US20150154954A1 - Initiating actions based on partial hotwords - Google Patents
Initiating actions based on partial hotwords Download PDFInfo
- Publication number
- US20150154954A1 US20150154954A1 US14/220,781 US201414220781A US2015154954A1 US 20150154954 A1 US20150154954 A1 US 20150154954A1 US 201414220781 A US201414220781 A US 201414220781A US 2015154954 A1 US2015154954 A1 US 2015154954A1
- Authority
- US
- United States
- Prior art keywords
- hotword
- actions
- audio data
- utterance
- action
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000000977 initiatory effect Effects 0.000 title description 4
- 230000009471 action Effects 0.000 claims abstract description 331
- 238000000034 method Methods 0.000 claims abstract description 52
- 230000004044 response Effects 0.000 claims abstract description 29
- 238000013518 transcription Methods 0.000 claims description 29
- 230000035897 transcription Effects 0.000 claims description 29
- 230000000875 corresponding effect Effects 0.000 claims description 14
- 230000003213 activating effect Effects 0.000 claims 1
- 238000004590 computer program Methods 0.000 abstract description 10
- 239000003999 initiator Substances 0.000 description 90
- 230000015654 memory Effects 0.000 description 34
- 230000008569 process Effects 0.000 description 22
- 238000004891 communication Methods 0.000 description 18
- 238000001514 detection method Methods 0.000 description 10
- 238000013507 mapping Methods 0.000 description 5
- 230000002441 reversible effect Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000002730 additional effect Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000036316 preload Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 230000002618 waking effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L2015/088—Word spotting
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Definitions
- the present disclosure discusses initiating actions based on partial hotwords, and, more specifically, providing an initial action in response to detecting the partial hotword.
- Vocal utterances may include a hotword, i.e., a predetermined reserved word that causes a system to perform a corresponding action or actions.
- a speech recognition service on an electronic device generally receives the vocal utterances that include spoken words from a user, and transcribes the spoken words into text. To accomplish this, the speech recognition service may attempt to match the sounds of the spoken input with phonetic representations of textual words.
- the detection of an initial portion of a hotword causes an action to be performed.
- a user may say a hotword such as “OK Google” to a mobile computing device that causes actions to be performed by the mobile computing device.
- the hotword “OK Google” causes the mobile computing device to wake from a sleep or stand-by state.
- the mobile computing device can cause certain actions to be performed that are associated with the full hotword “OK Google.” For instance, upon detection of the partial hotword “OK,” the mobile computing device can open a network connection.
- identifying one or more acoustic features of the initial portion of the audio data identifying one or more acoustic features of the initial portion of the audio data; comparing the one or more acoustic features of the initial portion of the audio data to one or more acoustic features associated with one or more hotwords stored in a database; and based on the comparing, determining that the initial portion of the audio data corresponds to the initial portion of the hotword of the one or more hotwords stored in the database.
- the initial portion of the hotword includes less than the entire hotword.
- the one or more actions of the subset include actions that are not visible to a user of a computing device performing the actions.
- the one or more actions of the subset of includes actions that are performed in a background computing environment of a computing device performing the actions.
- the interrupt signal causes the operating system to initialize a camera functionality of the computing device.
- the interrupt signal causes the operating system to activate the computing device from a sleep state.
- the interrupt signal causes the operating system to initialize a network connection on the computer device.
- the interrupt signal causes the operating system to preload an application on the computing device associated with the hotword.
- the features further include, for example, receiving a subsequent portion of the audio data; determining that the initial portion of the audio data and the subsequent portion of the audio data, collectively correspond to the entire hotword; in response to determining that the initial portion of the audio data and the subsequent portion of the audio data, collectively, correspond to the entire hotword, selecting, from among the set of one or more actions that are performed when the entire hotword is detected, an additional subset of the one or more actions; and causing the one or more actions of the additional subset to be performed.
- the set of the one or more actions includes the subset of the one or more actions and the additional subset of the one more actions.
- receiving Prior to receiving the audio data, receiving (i) data indicating the initial portion of the audio data corresponds to the initial portion of the hotword and (ii) data indicating the subset of the actions associated with the hotword.
- the hotword is a particular term that triggers semantic interpretation of an additional term of one or more terms that follow the particular term.
- FIG. 1 depicts an example system for detecting partial hotwords.
- FIGS. 2A-2F depict swim-lane diagrams of example processes for detecting partial hotwords.
- FIG. 3 depicts an example flowchart for detecting partial hotwords.
- FIG. 4 depicts a computer device and a mobile computer device that may be used to implement the techniques described here.
- FIG. 1 depicts a system 100 for detecting partial hotwords.
- the system 100 includes an audio subsystem 102 , a partial hotword action initiator 104 , a hotword detector 106 , a hotword-to-action mapper 108 , a hotword-to-action database 110 , and an action engine 112 .
- the system 100 is a mobile computing device, e.g., a mobile computing device 100 .
- the mobile computing device includes a smartphone, or tablet-computing device.
- the mobile computing device 100 can include any audio detection means, e.g., a microphone, for detecting utterances from a user 116 .
- the user 116 says one or more words that the mobile computing device 100 detects.
- the utterance includes one or more hotwords, or partial hotwords, that cause an action to be performed by the mobile computing device 100 .
- the user 116 says “OK Google.”
- the mobile computing device 100 detects the utterance “OK Google” with the audio subsystem 102 appropriately receiving audio data of the utterance “OK Google.”
- the audio subsystem 102 receives the initial portion of the audio data associated with the utterance “OK” at a time t 1 .
- the initial portion of the audio data can include a first few audio frames of the utterance, or a first few hundred milliseconds of audio data associated with the utterance.
- the audio subsystem 102 processes the utterance to generate waveform data that includes a portion of the utterance, or substantially a whole portion of the utterance.
- the audio subsystem 102 appropriately processes the received audio data. For example, the audio subsystem 102 identifies one or more acoustic features of the initial portion of the audio data. In the illustrated example, the audio subsystem 102 identifies acoustic features associated with the initial portion of the audio data associated with the utterance “OK.” In some examples, the audio subsystem 102 obtains a transcription of the initial portion of the audio data associated with the utterance “OK.” In the illustrated example, the audio subsystem 102 obtains a transcription of the initial portion of the audio data associated with the utterance “OK.”
- the audio subsystem 102 provides the processed audio data to the partial hotword action initiator 104 .
- the audio subsystem 102 provides the processed audio data associated with the utterance “OK” to the partial hotword action initiator 104 .
- the processed audio data can include acoustic features associated with the utterance “OK,” a transcription associated with the utterance “OK,” or both.
- the partial hotword action initiator 104 receives the processed audio data from the audio subsystem 102 .
- the processed audio data can include audio data associated with the utterance “OK,” acoustic features associated with the utterance “OK,” a transcription associated with the utterance “OK,” or any combination thereof.
- the partial hotword action initiator 104 provides the processed audio data to the hotword detector 106 .
- the hotword detector 106 receives the processed audio data from the partial hotword action initiator 104 .
- the hotword detector 106 initially receives the processed audio data associated with the utterance “OK,” e.g., an initial portion of the audio data.
- the hotword detector 106 determines that the received audio data corresponds to an initial portion of a hotword.
- the hotword detector 106 includes a partial hotword detector 118 .
- the partial hotword detector 118 determines that the initial portion of the audio data corresponds to an initial portion of a hotword.
- the partial hotword detector 118 determines that the initial portion of the audio data associated with the utterance “OK” corresponds to an initial portion of a hotword “OK Google.”
- the initial portion of a hotword includes less than the entire hotword. For example, the initial portion “OK” is less than the entire hotword “OK Google.”
- the received audio data includes associated acoustic features, e.g., as identified by the audio subsystem 102 .
- the partial hotword detector 118 compares the acoustic features of the initial portion of the audio data associated with the utterance “OK” to acoustic features associated with one or more hotwords stored in a database.
- each hotword is associated with one or more acoustic features, e.g., phonetics of the hotword.
- a database, or table stores a mapping between the hotwords and an associated acoustic feature(s).
- a hotword is associated with two or more acoustic features.
- an acoustic feature is associated with two or more hotwords.
- the initial portion of the audio data associated with the utterance “OK” is determined to correspond to an initial portion of a hotword stored in the database. For example, it is determined that the acoustic features of the initial portion of the audio data associated with the utterance “OK” corresponds to an initial portion of a hotword “OK Google” based on the comparison of the acoustic features of the utterance “OK” and the acoustic features of the hotword “OK Google.”
- the processed audio data includes a transcription, e.g., as obtained by the audio subsystem 102 .
- the partial hotword detector 118 compares the transcription of the initial portion of the audio data associated with the utterance “OK,” to transcriptions associated with hotwords stored in a database. Specifically, a hotword is associated with a transcription.
- a database, or table, stores a mapping between the hotword and a transcription.
- the transcription of the initial portion of the audio data associated with the partial utterance “OK” is determined to correspond to an initial portion of a hotword stored in a database. For example, it is determined that the transcription of the initial portion of the audio data associated with the utterance “OK” corresponds to an initial portion of a hotword “OK Google” based on the comparison of the transcription of the utterance “OK” and the transcription of the hotword “OK Google.”
- the hotword detector 106 provides a result of the determination that the initial portion of the audio data corresponds to the initial portion of a hotword to the partial hotword action initiator 104 . Specifically, in the illustrated example, the hotword detector 106 provides the partial hotword “OK,” or a signal associated with the partial hotword “OK,” to the partial hotword action initiator 104 .
- the partial hotword action initiator 104 receives the result of the determination from the hotword detector 106 . Specifically, in the illustrated example, the partial hotword action initiator 104 receives the partial hotword “OK,” or a signal associated with the partial hotword “OK,” from the hotword detector 106 . The signal can include an indication that the initial portion of the audio data associated with the utterance “OK” corresponds to an initial portion of a hotword. In response, the partial hotword action initiator 104 provides the partial hotword “OK,” or the signal associated with the partial hotword “OK,” to the hotword-to-action mapper 108 .
- the hotword-to-action mapper 108 receives the result of the determination that the initial portion of the audio data corresponds to the initial portion of the hotword from the partial hotword action initiator 104 . Specifically, in the illustrated example, the hotword-to-action mapper 108 receives the partial hotword “OK,” or the signal associated with the partial hotword “OK,” from the partial hotword action initiator 104 . The hotword-to-action mapper 108 selects, from among a set of actions that are performed when the entire hotword is detected, a subset of the actions. Specifically, each hotword is associated with one or more actions, e.g., actions that are performed when the entire hotword is detected.
- a hotword-to-action database 110 stores mapping between hotwords and associated actions. In some examples, a hotword is mapped to two or more actions. In some examples, an action is mapped to two or more hotwords.
- the hotword-to-action mapper 108 upon detection of the partial hotword “OK,” the hotword-to-action mapper 108 identifies a particular set of actions that are associated with the entire hotword “OK Google.” That is, the hotword-to-action mapper 108 is in communication with the hotword-to-action database 110 to identify a mapping between the entire hotword “OK Google” and the particular set of actions from multiple sets of actions that are associated with the entire hotword “OK Google.” The hotword-to-action mapper 108 selects a subset of actions from among the particular set of actions associated with the entire hotword “OK Google.” Specifically, the hotword-to-action mapper 108 selects the subset of actions that are further associated with the partial hotword “OK” of the entire hotword “OK Google.” In some examples, the hotword-to-action mapper 108 identifies the subset of actions that are associated with the partial hotword “OK.”
- the hotword-to-action mapper 108 can use multiple criteria for selecting the subset of actions. For example, the hotword-to-action mapper 108 can select actions from the particular set of actions that are not visible to the user. That is, select actions that are not visible to the user that include actions caused to be performed by the mobile computing device 116 that are not readably noticeable or detectable by the user 116 , e.g., visually or audible detectable by the user 116 .
- the actions can include actions that are not shown on a user interface of the mobile computing device 100 , or actions that do not make noise by the mobile computing device 100 .
- the selected actions can include actions that are performed in a background computing environment of the mobile computing device 100 .
- the subset of actions include an action of establishing a network connection, e.g., with a third-party computing server or a back-end computing server.
- the selected actions can include actions that have no lasting or permanent effects, i.e., are reversible, on the mobile computing device
- the hotword-to-action mapper 108 provides data identifying the subset of actions to the partial hotword action interior 104 . Specifically, the hotword-to-action mapper 108 provides data identifying the subset of actions associated with the hotword “OK Google” to the partial hotword action initiator 104 .
- the partial hotword action initiator 104 receives the data identifying the subset of actions from the hotword-to-action mapper 108 , and in response, provides the data identifying the subset of actions to the action engine 112 . Specifically, by providing the data identifying the subset of actions to the action engine 112 , the partial hotword action initiator 104 causes the subset of actions to be performed.
- the action engine 112 receives the data identifying the subset of actions from the partial hotword action initiator 104 .
- the action engine 112 receives the data identifying the subset of actions associated with the initial portion of the hotword “OK Google,” as selected by the hotword-to-action mapper 108 .
- the action engine 112 causes an action of establishing a network connection to be performed, e.g., by the operating system executing on the mobile computing device 100 .
- causing the subset of actions to be performed includes transmitting an interrupt signal to the operating system executing on the mobile computing device 100 .
- the interrupt signal causes the operating system to initialize a camera functionality of the mobile computing device 100 .
- the interrupt signal causes the operating stem to activate the mobile computing device 100 from a sleep state. That is, that state of the mobile computing device 100 is changed from a sleep state, or an “off” state, to a wake state, or an “on” state.
- the interrupt signal causes the operating system to preload an application stored on the mobile computing device 100 that is associated with the hotword. That is, the application can be preloaded into a memory of the mobile computing device 100 .
- the audio subsystem 102 receives a subsequent portion of the audio data. For example, the audio subsystem 102 receives the subsequent portion of the detected utterance, e.g., subsequent to the initial portion of the audio data. In the illustrated example, the audio subsystem 102 receives the subsequent portion of the audio data associated with the utterance “Google” at a time t 2 . The audio subsystem 102 appropriately processes the received audio data. In some examples, the audio subsystem 102 receives a whole portion of the audio, including the initial portion and the subsequent portion.
- the hotword is a particular term that triggers semantic interpretation of an additional term of one or more terms that follow the particular term. For example, by the initial portion of the audio data associated with the utterance “OK” corresponding to an initial portion of a hotword, the audio subsystem 102 provides a semantic interpretation of the subsequent portion of the audio data associated with the utterance “Google.”
- the audio subsystem 102 provides the processed audio data associated with the entire utterance to the partial hotword action initiator 104 .
- the audio subsystem 102 provides the processed audio data associated with the utterance “OK Google” to the partial hotword action initiator 104 .
- the processed audio data can include acoustic features associated with the utterance “OK Google,” a transcription associated with the utterance “OK Google,” or both.
- the partial hotword action initiator 104 receives the processed audio data from the audio subsystem 102 .
- the processed audio data can include the audio data associated with the utterance “OK Google,” acoustic features associated with the audio data associated with the utterance “OK Google,” a transcription associated with the audio data associated with the utterance “OK Google,” or any combination thereof.
- the partial hotword action initiator 104 provides the processed audio data to the hotword detector 106 .
- the hotword detector 106 receives the processed audio data from the partial hotword action initiator 104 .
- the hotword detector 106 receives the processed audio data associated with the initial portion of the audio associated with the utterance “OK” and the subsequent portion of the audio data associated with the utterance “Google.”
- the hotword detector 106 receives the audio data associated with the entire utterance “OK Google.”
- the hotword detector 106 determines that the initial and the subsequent portion of the audio data, collectively, correspond to the entire hotword “OK Google.”
- the hotword detector 106 provides a result of the determination that the initial portion and the subsequent portion of the audio data associated with the utterance “OK Google” collectively correspond to the entire hotword to the partial hotword action initiator 104 .
- the hotword detector 106 provides the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” to the partial hotword action initiator 104 .
- the signal can include an indication that the initial portion and the subsequent portion of the audio data, collectively, correspond to an entire hotword.
- the partial hotword action initiator 104 receives the result of the determination from the hotword detector 106 . Specifically, in the illustrated example, the partial hotword action initiator 104 receives the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” from the hotword detector 106 . In response, the partial hotword action initiator 104 provides the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” to the hotword-to-action mapper 108 .
- the hotword-to-action mapper 108 receives the result, e.g., a signal, of the determination that the initial portion and the subsequent portion of the audio data associated with the utterance “OK Google” collectively correspond to the entire hotword from the partial hotword action initiator 104 . Specifically, in the illustrated example, the hotword-to-action mapper 108 receives the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” from the partial hotword action initiator 104 . The hotword-to-action mapper 108 selects, from among a set of actions that are performed when the entire hotword is detected, an additional subset of the actions.
- the result e.g., a signal
- the hotword-to-action mapper 108 upon receipt of the entire hotword “OK Google,” or the signal associated with the entire hotword “OK Google,” the hotword-to-action mapper 108 identifies a particular set of actions that are associated with the entire hotword “OK Google.” That is, the hotword-to-action mapper 108 is in communication with the hotword-to-action database 110 to identify a mapping between the entire hotword “OK Google” and the particular set of actions from multiple sets of actions. The hotword-to-action mapper 108 selects an additional subset of actions from among the particular set of actions associated with the entire hotword “OK Google.” In some examples, the set of actions associated with the entire hotword “OK Google” includes the subset of actions and the additional subset of actions.
- the additional subset of actions includes the subset of actions. In some examples, the additional subset of actions includes one or more actions of the subset of actions. For example, upon detection of the entire hotword “OK Google,” each action of the subset of actions may have not been fully performed by the action engine 112 . Thus, any unperformed actions associated with the subset of actions can further be included by the additional subset of actions.
- the hotword-to-action mapper 108 provides data identifying the additional subset of actions to the partial hotword action initiator 104 . That is, the hotword-to-action mapper 108 provides data identifying the additional subset of actions associated with the detection of the entire hotword “OK Google” to the partial hotword action initiator 104 .
- the partial hotword action initiator 104 receives the data identifying the additional subset of actions from the hotword-to-action mapper 108 , and in response, provides the data identifying the additional subset of actions to the action engine 112 . Specifically, by providing the data identifying the additional subset of actions to the action engine 112 , the partial hotword action initiator 104 causes the additional subset of actions to be performed.
- the action engine 112 receives the data identifying the additional subset of actions from the partial hotword action initiator 104 .
- the action engine 112 receives the data identifying the additional subset of actions associated with the detection of the entire hotword, as selected by the hotword-to-action mapper 108 .
- the additional subset of actions that are associated with the entire hotword “OK Google” are performed at the time t 2 .
- the action engine 112 causes an action of turning a display, or screen, of the mobile computing device 100 to be in an “on” state.
- the action engine 112 causes an action of displaying a user interface.
- the set of actions associated with the detection of the partial hotword “OK” and the additional set of actions associated with the detection of the entire hotword “OK Google” are caused to be performed by the action engine 112 in parallel, or at substantially the same time.
- additional data is received (i) indicating that the initial portion of the audio data corresponds to the initial portion of the hotword and additional data (ii) indicating the subset of the actions associated with the hotword.
- the mobile computing device 100 is “trained,” e.g., receives the additional data, such that the partial hotword detector 118 is able to determine whether an initial portion of the audio data, e.g., the “OK” utterance, corresponds to an initial portion of a hotword, e.g., “OK Google.”
- the mobile computing device 100 receives the additional data such that the hotword-to-action-mapper 108 and the hotword-to-action database 110 are able to identify a subset of actions associated with the hotword “OK Google.” That is, the hotword-to-action-mapper 108 receives data such that the hotword-to-action database 110 maps associations between hotwords
- FIG. 2 illustrates a swim-lane diagram of interactions between an audio subsystem 295 , a partial hotword action initiator 296 , a hotword detector 297 , a hotword-to-action mapper 298 , and an action engine 299 .
- the audio subsystem 295 can include the audio subsystem 102 of FIG. 1 ;
- the partial hotword action initiator 296 can include the partial hotword initiator 104 of FIG. 1 ;
- the hotword detector 297 can include the hotword detector 106 , the partial hotword detector 118 , or both, of FIG. 1 ;
- the hotword-to-action mapper 298 can include the hotword-to-action mapper 108 of FIG.
- the action engine 299 can include the action engine 112 of FIG. 1 .
- a user e.g., the user 116
- the audio subsystem 295 receives and appropriately processes the partial utterance “OK.”
- the partial hotword action initiator 296 receives the processed partial utterance “OK” and forwards the same to the hotword detector 297 .
- the hotword detector 297 determines that the partial utterance “OK” corresponds to, at least, an initial portion of the hotword “OK Google.” In some examples, the partial utterance “OK” can correspond to an initial portion of two or more hotwords.
- the hotword detector 297 provides the determination, or result, to the partial hotword action initiator 296 .
- the partial hotword detector 296 determines that the partial utterance “OK” correspond to an initial portion of a hotword “OK Google.”
- the partial hotword action initiator 296 receives the determination, or result, and at step 206 , in response, triggers the hotword-to-action mapper 298 .
- the partial hotword action initiator 296 in response to the partial utterance “OK” corresponding to an initial portion of a hotword, triggers the hotword-to-action-mapper 298 by providing the partial hotword “OK,” or a signal associated with the partial hotword “OK,” to the hotword-to-action initiator 298 .
- the hotword-to-action mapper 298 maps the partial hotword “OK” of the entire hotword “OK Google” to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the partial hotword “OK” of the hotword “OK Google” to a network connection action, e.g., initializing or opening a network connection.
- the hotword-to-action mapper 298 provides information associated with the network connection action to the partial hotword action initiator 296 .
- the partial hotword action initiator 296 receives the information associated with the network connection action.
- the partial hotword action initiator 296 causes the network connection action to be performed.
- the partial hotword action initiator 296 provides the information associated with the network connection action to the action engine 299 .
- the action engine 299 appropriately processes the network connection action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the network connection action.
- the audio subsystem 295 receives and appropriately processes the partial utterance “computer.”
- the partial hotword action initiator 296 receives the processed partial utterance “computer” and forwards the same to the partial hotword detector 118 .
- the hotword detector 297 determines that the entire utterance “OK computer” does not correspond to, at least, the entire hotword “OK Google,” or any other hotword. Specifically, in the illustrated example, the hotword detector 297 determines that the initial portion and the subsequent portion of the utterance “OK computer” does not correspond to an entire hotword.
- the processed audio data includes associated acoustic features, e.g., as identified by the audio subsystem 102 .
- the hotword detector 297 can compare the acoustic features of the audio data associated with the entire utterance “OK computer” to acoustic features associated with one or more hotwords stored in a database. Based on the comparing of acoustic features, the audio data associated with the entire utterance “OK computer” is determined not to correspond to a hotword stored in the database.
- the processed audio data includes a transcription, e.g., as obtained by the audio subsystem 295 .
- the hotword detector 297 can compare the transcription of the audio data associated with the entire utterance “OK computer” to transcriptions associated with hotwords stored in a database. Based on the comparing of transcriptions, the audio data associated with the entire utterance “OK computer” is determined not to correspond to a hotword stored in a database.
- the hotword detector 297 provides the determination, or result, to the partial hotword action initiator 296 .
- the hotword detector 297 determines that the entire utterance “OK computer” does not correspond to a hotword.
- the partial hotword action initiator 296 receives the determination, or result, and at step 220 , in response, triggers the hotword-to-action mapper 298 .
- the partial hotword action initiator 297 triggers the hotword-to-action-mapper 298 .
- the hotword-to-action mapper 298 selects an additional subset of actions that when performed, cause the open network connection action to be reversed, or cancelled.
- each particular action corresponding to a hotword can further be associated with one or more additional actions that when selected, reverse the particular action that was previously performed.
- the open network connection action as performed at step 211 , can be associated with a close network connection action such that when the hotword “OK Google” is not detected, e.g., after detecting the partial hotword “OK,” the open network connection action is reversed.
- each particular action can be associated with two or more additional actions that reverse the particular action, e.g., negate the particular action.
- the hotword-to-action mapper 298 provides information associated with the close network connection action to the partial hotword action initiator 296 .
- the partial hotword action initiator 296 receives the information associated with the close network connection action.
- the partial hotword action initiator 296 causes the close network connection action to be performed. That is, the partial hotword action initiator 296 provides the information associated with the close network connection action to the action engine 299 .
- the action engine 299 appropriately processes the close network connection action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the close network connection action.
- the audio subsystem 295 receives and appropriately processes the utterance “I mean.”
- the partial hotword action initiator 296 receives the processed utterance “I mean” and forwards the same to the hotword detector 297 .
- the hotword detector 297 determines that the utterance “I mean” does not corresponds to, at least, an initial portion of a hotword or an entire hotword.
- the hotword detector 297 provides the determination, or result, to the partial hotword action initiator 296 .
- the partial hotword action initiator 296 receives the determination, or result, and, in response to the utterance “I mean” not corresponding to an initial portion of a hotword or an entire hotword, takes no further action.
- the audio subsystem 295 receives and appropriately processes the partial utterance “OK.”
- the partial hotword action initiator 295 receives the processed partial utterance “OK” and forwards the same to the hotword detector 297 .
- the hotword detector 297 determines that the partial utterance “OK” corresponds to, at least, an initial portion of the hotword “OK Google.”
- the hotword detector 297 provides the determination, or result, to the partial hotword action initiator 296 .
- the hotword detector 297 determines that the partial utterance “OK” correspond to an initial portion of a hotword “OK Google.”
- the partial hotword action initiator 296 receives the determination, or result, and at step 240 , in response, triggers the hotword-to-action mapper 298 .
- the partial hotword action initiator 296 in response to the partial utterance “OK” corresponding to an initial portion of a hotword, triggers the hotword-to-action-mapper 298 by providing the partial hotword “OK,” or a signal associated with the partial hotword “OK,” to the hotword-to-action mapper 298 .
- the hotword-to-action mapper 298 maps the partial hotword “OK” to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the partial hotword “OK” of the entire hotword “OK Google” to a network connection action, e.g., initializing or opening a network connection.
- the hotword-to-action mapper 298 provides information associated with the network connection action to the partial hotword action initiator 296 .
- the partial hotword action initiator 296 receives information associated with the network connection action.
- the partial hotword action initiator 296 causes the network connection action to be performed.
- the partial hotword action initiator 296 provides the information associated with the network connection action to the action engine 299 .
- the action engine 299 appropriately processes the network connection action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the network connection action.
- the audio subsystem 295 receives and appropriately processes the partial utterance “Google.”
- the partial hotword action initiator 296 receives the processed partial utterance “Google” and forwards the same to the hotword detector 297 .
- the hotword detector 297 determines that the utterance “OK Google” corresponds to, at least, a hotword “OK Google.”
- the hotword detector 297 provides the determination, or result, to the partial hotword action initiator 296 .
- the partial hotword detector 297 determines that the initial utterance “OK” and the subsequent utterance “Google,” collectively correspond to the hotword “OK Google.”
- the partial hotword action initiator 296 receives the determination, or result, and at step 255 , in response, triggers the hotword-to-action mapper 298 .
- the partial hotword action initiator 296 in response to the initial utterance “OK” and the subsequent utterance “Google,” collectively, corresponding to an entire hotword, the partial hotword action initiator 296 triggers the hotword-to-action-mapper 298 by providing the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” to the hotword-to-action mapper 298 .
- the hotword-to-action mapper 298 maps the hotword to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the hotword “OK Google” to a wake mobile device action, e.g., waking the mobile computing device from a sleep state, or “off state,” to a wake state, or an “on” state.
- the hotword-to-action mapper 298 provides information associated with the wake mobile device action to the partial hotword action initiator 296 .
- the partial hotword action initiator 296 receives information associated with the wake mobile device action.
- the partial hotword action initiator 296 causes the wake mobile device action to be performed.
- the partial hotword action initiator 296 provides the information associated with the wake mobile device action to the action engine 299 .
- the action engine 299 appropriately processes the wake mobile device action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the wake mobile device action.
- the audio subsystem 295 receives and appropriately processes the partial utterance “Call.”
- the partial hotword action initiator 296 receives the processed partial utterance “Call” and forwards the same to the hotword detector 297 .
- the hotword detector 297 determines that the partial utterance “Call” corresponds to, at least, an initial portion of a hotword.
- the hotword detector 297 provides the determination, or result, to the partial hotword action initiator 296 . For example, the hotword detector 297 determines that the partial utterance “Call” correspond to an initial portion of a hotword.
- the partial hotword action initiator 296 receives the determination, or result, and at step 270 , in response, triggers the hotword-to-action mapper 298 .
- the partial hotword action initiator 296 triggers the hotword-to-action-mapper 298 by providing the partial hotword “Call” to the hotword-to-action mapper 108 .
- the hotword-to-action mapper 298 maps the partial hotword of the hotword to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the partial hotword “Call” to a launch telephone application action, e.g., preloading of an application on a mobile computing device.
- the hotword-to-action mapper 298 provides information associated with the launch telephone application action to the partial hotword action initiator 296 .
- the partial hotword action initiator 296 receives information associated with the launch telephone application action.
- the partial hotword action initiator 296 causes the launch telephone application action to be performed.
- the partial hotword action initiator 296 provides the information associated with the launch telephone application action to the action engine 299 .
- the action engine 299 appropriately processes the launch telephone application action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the launch telephone application action.
- the audio subsystem 295 receives and appropriately processes the partial utterance “Mom.”
- the partial hotword action initiator 296 receives the processed partial utterance “Mom” and forwards the same to the hotword detector 297 .
- the hotword detector 297 determines that the initial utterance “Call” and the subsequent utterance “Mom,” collectively, correspond to, at least, the hotword “Call Mom.”
- the hotword detector 297 provides the determination, or result, to the partial hotword action initiator 296 .
- the hotword detector 297 determines that the initial utterance “Call” and the subsequent utterance “Mom,” collectively, correspond to an entire hotword.
- the partial hotword action initiator 296 receives the determination, or result, and at step 285 , in response, triggers the hotword-to-action mapper 298 .
- the partial hotword action initiator 296 triggers the hotword-to-action-mapper 298 by providing the entire hotword “Call Mom” to the hotword-to-action mapper 298 .
- the hotword-to-action mapper 298 maps the entire hotword “Call Mom” to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the entire hotword “Call Mom” to a contact assigned with the utterance “Mom.” The user may have previously associated the utterance “Mom” with a contact stored by a mobile computing device.
- the hotword-to-action mapper 298 provides information associated with the place call to “Mom” action to the partial hotword action initiator 296 .
- the partial hotword action initiator 296 receives information associated with the place call to “Mom” action.
- the information can include contact information associated with a contact “Mom.”
- the partial hotword action initiator 296 causes the call to be placed to “Mom” action to be performed. That is, the partial hotword action initiator 296 provides the information associated with the call to be placed to “Mom” action to the action engine 299 .
- the action engine 299 appropriately processes the call to be placed to “Mom” action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the call to be placed to “Mom” action.
- FIG. 3 depicts a flowchart of an example process 300 for identifying partial hotwords.
- the example process 300 can be executed using one or more computing devices.
- the audio subsystem 102 , the partial hotword action initiator 104 , the hotword detector 106 , the hotword to action mapper 108 , the hotword-to-action database 110 , the action engine 112 , and the partial hotword detector 118 can be used to execute the example process 300 .
- Audio data is received ( 302 ).
- the audio subsystem 102 receives the audio data of an utterance “OK Google” from the mobile computing device 114 .
- An initial portion of the audio data is determined to correspond to an initial portion of a hotword ( 304 ).
- the hotword detector 106 , the partial hotword detector 118 , or both determine that the initial portion “OK” of the audio data “OK Google” corresponds to an initial portion of a hotword.
- a subset of one or more actions are selected from among a set of one or more actions that are performed when the entire hotword is detected ( 306 ).
- the hotword-to-action mapper 108 identifies a particular set of actions that are associated with the entire hotword “OK Google.” The hotword-to-action mapper 108 selects the subset of actions that are further associated with the partial hotword “OK” of the entire hotword “OK Google.” One or more actions of the subset are caused to be performed ( 308 ). For example, the action engine 112 receives the subset of actions associated with the entire hotword “OK Google” that are caused to be performed.
- FIG. 4 shows an example of a generic computer device 400 and a generic mobile computer device 450 , which may be used with the techniques described here.
- Computing device 400 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers.
- Computing device 450 is intended to represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, and other similar computing devices.
- the components shown here, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed in this document.
- Computing device 400 includes a processor 402 , memory 404 , a storage device 406 , a high-speed interface 408 connecting to memory 404 and high-speed expansion ports 410 , and a low speed interface 412 connecting to low speed bus 414 and storage device 406 .
- Each of the components 402 , 404 , 406 , 408 , 410 , and 412 are interconnected using various busses, and may be mounted on a common motherboard or in other manners as appropriate.
- the processor 402 may process instructions for execution within the computing device 400 , including instructions stored in the memory 404 or on the storage device 406 to display graphical information for a GUI on an external input/output device, such as display 416 coupled to high speed interface 408 .
- multiple processors and/or multiple buses may be used, as appropriate, along with multiple memories and types of memory.
- multiple computing devices 400 may be connected, with each device providing portions of the necessary operations (e.g., as a server bank, a group of blade servers, or a multi-processor system).
- the memory 404 stores information within the computing device 400 .
- the memory 404 is a volatile memory unit or units.
- the memory 404 is a non-volatile memory unit or units.
- the memory 404 may also be another form of computer-readable medium, such as a magnetic or optical disk.
- the storage device 406 is capable of providing mass storage for the computing device 400 .
- the storage device 406 may be or contain a computer-readable medium, such as a floppy disk device, a hard disk device, an optical disk device, or a tape device, a flash memory or other similar solid state memory device, or an array of devices, including devices in a storage area network or other configurations.
- a computer program product may be tangibly embodied in an information carrier.
- the computer program product may also contain instructions that, when executed, perform one or more methods, such as those described above.
- the information carrier is a computer- or machine-readable medium, such as the memory 404 , the storage device 406 , or a memory on processor 402 .
- the high speed controller 408 manages bandwidth-intensive operations for the computing device 400 , while the low speed controller 412 manages lower bandwidth-intensive operations.
- the high-speed controller 408 is coupled to memory 404 , display 416 (e.g., through a graphics processor or accelerator), and to high-speed expansion ports 410 , which may accept various expansion cards (not shown).
- low-speed controller 412 is coupled to storage device 406 and low-speed expansion port 414 .
- the low-speed expansion port which may include various communication ports (e.g., USB, Bluetooth, Ethernet, wireless Ethernet) may be coupled to one or more input/output devices, such as a keyboard, a pointing device, a scanner, or a networking device such as a switch or router, e.g., through a network adapter.
- input/output devices such as a keyboard, a pointing device, a scanner, or a networking device such as a switch or router, e.g., through a network adapter.
- the computing device 400 may be implemented in a number of different forms, as shown in the figure. For example, it may be implemented as a standard server 420 , or multiple times in a group of such servers. It may also be implemented as part of a rack server system 424 . In addition, it may be implemented in a personal computer such as a laptop computer 422 . Alternatively, components from computing device 400 may be combined with other components in a mobile device (not shown), such as device 450 . Each of such devices may contain one or more of computing device 400 , 450 , and an entire system may be made up of multiple computing devices 400 , 450 communicating with each other.
- Computing device 450 includes a processor 452 , memory 464 , an input/output device such as a display 454 , a communication interface 466 , and a transceiver 468 , among other components.
- the device 450 may also be provided with a storage device, such as a microdrive or other device, to provide additional storage.
- a storage device such as a microdrive or other device, to provide additional storage.
- Each of the components 450 , 452 , 464 , 454 , 466 , and 468 are interconnected using various buses, and several of the components may be mounted on a common motherboard or in other manners as appropriate.
- the processor 452 may execute instructions within the computing device 640 , including instructions stored in the memory 464 .
- the processor may be implemented as a chipset of chips that include separate and multiple analog and digital processors.
- the processor may provide, for example, for coordination of the other components of the device 450 , such as control of user interfaces, applications run by device 450 , and wireless communication by device 450 .
- Processor 452 may communicate with a user through control interface 648 and display interface 456 coupled to a display 454 .
- the display 454 may be, for example, a TFT LCD (Thin-Film-Transistor Liquid Crystal Display) or an OLED (Organic Light Emitting Diode) display, or other appropriate display technology.
- the display interface 456 may comprise appropriate circuitry for driving the display 454 to present graphical and other information to a user.
- the control interface 458 may receive commands from a user and convert them for submission to the processor 452 .
- an external interface 462 may be provide in communication with processor 452 , so as to enable near area communication of device 450 with other devices. External interface 462 may provide, for example, for wired communication in some implementations, or for wireless communication in other implementations, and multiple interfaces may also be used.
- the memory 464 stores information within the computing device 450 .
- the memory 464 may be implemented as one or more of a computer-readable medium or media, a volatile memory unit or units, or a non-volatile memory unit or units.
- Expansion memory 454 may also be provided and connected to device 450 through expansion interface 452 , which may include, for example, a SIMM (Single In Line
- expansion memory 454 may provide extra storage space for device 450 , or may also store applications or other information for device 450 .
- expansion memory 454 may include instructions to carry out or supplement the processes described above, and may include secure information also.
- expansion memory 454 may be provide as a security module for device 450 , and may be programmed with instructions that permit secure use of device 450 .
- secure applications may be provided via the SIMM cards, along with additional information, such as placing identifying information on the SIMM card in a non-hackable manner.
- the memory may include, for example, flash memory and/or NVRAM memory, as discussed below.
- a computer program product is tangibly embodied in an information carrier.
- the computer program product contains instructions that, when executed, perform one or more methods, such as those described above.
- the information carrier is a computer- or machine-readable medium, such as the memory 464 , expansion memory 454 , memory on processor 452 , or a propagated signal that may be received, for example, over transceiver 468 or external interface 462 .
- Device 450 may communicate wirelessly through communication interface 466 , which may include digital signal processing circuitry where necessary. Communication interface 466 may provide for communications under various modes or protocols, such as GSM voice calls, SMS, EMS, or MMS messaging, CDMA, TDMA, PDC, WCDMA, CDMA2000, or GPRS, among others. Such communication may occur, for example, through radio-frequency transceiver 468 . In addition, short-range communication may occur, such as using a Bluetooth, WiFi, or other such transceiver (not shown). In addition, GPS (Global Positioning System) receiver module 450 may provide additional navigation- and location-related wireless data to device 450 , which may be used as appropriate by applications running on device 450 .
- GPS Global Positioning System
- Device 450 may also communicate audibly using audio codec 460 , which may receive spoken information from a user and convert it to usable digital information. Audio codec 460 may likewise generate audible sound for a user, such as through a speaker, e.g., in a handset of device 450 . Such sound may include sound from voice telephone calls, may include recorded sound (e.g., voice messages, music files, etc.) and may also include sound generated by applications operating on device 450 .
- Audio codec 460 may receive spoken information from a user and convert it to usable digital information. Audio codec 460 may likewise generate audible sound for a user, such as through a speaker, e.g., in a handset of device 450 . Such sound may include sound from voice telephone calls, may include recorded sound (e.g., voice messages, music files, etc.) and may also include sound generated by applications operating on device 450 .
- the computing device 450 may be implemented in a number of different forms, as shown in the figure. For example, it may be implemented as a cellular telephone 480 . It may also be implemented as part of a smartphone 482 , personal digital assistant, or other similar mobile device.
- implementations of the systems and techniques described here may be realized in digital electronic circuitry, integrated circuitry, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof.
- ASICs application specific integrated circuits
- These various implementations may include implementation in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.
- the systems and techniques described here may be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user may provide input to the computer.
- a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
- a keyboard and a pointing device e.g., a mouse or a trackball
- Other kinds of devices may be used to provide for interaction with a user as well; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
- the systems and techniques described here may be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a client computer having a graphical user interface or a Web browser through which a user may interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components.
- the components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (“LAN”), a wide area network (“WAN”), and the Internet.
- LAN local area network
- WAN wide area network
- the Internet the global information network
- the computing system may include clients and servers.
- a client and server are generally remote from each other and typically interact through a communication network.
- the relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
Abstract
Description
- This application is a continuation of U.S. patent application Ser. No. 14/096,359, entitled “Initiating Actions Based On Partial Hotwords,” filed Dec. 4, 2013, which is incorporated herein by reference in its entirety.
- The present disclosure discusses initiating actions based on partial hotwords, and, more specifically, providing an initial action in response to detecting the partial hotword.
- Vocal utterances may include a hotword, i.e., a predetermined reserved word that causes a system to perform a corresponding action or actions. A speech recognition service on an electronic device generally receives the vocal utterances that include spoken words from a user, and transcribes the spoken words into text. To accomplish this, the speech recognition service may attempt to match the sounds of the spoken input with phonetic representations of textual words.
- According to some innovative aspects of the subject matter described in this specification, the detection of an initial portion of a hotword causes an action to be performed. A user may say a hotword such as “OK Google” to a mobile computing device that causes actions to be performed by the mobile computing device. For example, the hotword “OK Google” causes the mobile computing device to wake from a sleep or stand-by state.
- Upon detection of an initial portion of the hotword, e.g., the “OK” portion of the hotword “OK Google,” the mobile computing device can cause certain actions to be performed that are associated with the full hotword “OK Google.” For instance, upon detection of the partial hotword “OK,” the mobile computing device can open a network connection. By causing a subset of the actions that are associated with the hotword to be performed after detecting an initial portion of the hotword can reduce latency associated with the hotword, and thus, the processing time associated with the hotword is reduced, while being transparent to the user. That is, the user perceives a speed improvement of the mobile computing device.
- Innovative aspects of the subject matter described in this specification may be embodied in methods that include the actions of receiving audio data; determining that an initial portion of the audio data corresponds to an initial portion of a hotword; in response to determining that the initial portion of the audio data corresponds to the initial portion of the hotword, selecting, from among a set of one or more actions that are performed when the entire hotword is detected, a subset of the one or more actions; and causing one or more actions of the subset to be performed
- Other embodiments of these aspects include corresponding systems, apparatus, and computer programs, configured to perform the actions of the methods, encoded on computer storage devices.
- These and other embodiments may each optionally include one or more of the following features. For instance, identifying one or more acoustic features of the initial portion of the audio data; comparing the one or more acoustic features of the initial portion of the audio data to one or more acoustic features associated with one or more hotwords stored in a database; and based on the comparing, determining that the initial portion of the audio data corresponds to the initial portion of the hotword of the one or more hotwords stored in the database. Obtaining a transcription of the initial portion of the audio data, the audio data including a speech utterance; comparing the transcription of the initial portion of the audio to one or more transcriptions associated with one or more hotwords stored in a database; and based on the comparing, determining that the initial portion of the audio corresponding to the initial portion of the hotword of the one or more hotwords stored in the database. The initial portion of the hotword includes less than the entire hotword. Tthe one or more actions of the subset include actions that are not visible to a user of a computing device performing the actions. The one or more actions of the subset of includes actions that are performed in a background computing environment of a computing device performing the actions. Transmitting an interrupt signal to an operating system executing on a computing device to perform the one or more actions. The interrupt signal causes the operating system to initialize a camera functionality of the computing device. The interrupt signal causes the operating system to activate the computing device from a sleep state. The interrupt signal causes the operating system to initialize a network connection on the computer device. The interrupt signal causes the operating system to preload an application on the computing device associated with the hotword.
- The features further include, for example, receiving a subsequent portion of the audio data; determining that the initial portion of the audio data and the subsequent portion of the audio data, collectively correspond to the entire hotword; in response to determining that the initial portion of the audio data and the subsequent portion of the audio data, collectively, correspond to the entire hotword, selecting, from among the set of one or more actions that are performed when the entire hotword is detected, an additional subset of the one or more actions; and causing the one or more actions of the additional subset to be performed. The set of the one or more actions includes the subset of the one or more actions and the additional subset of the one more actions. Receiving a subsequent portion of the audio data; determining that the initial portion of the audio data and the subsequent portion of the audio data, collectively, do not correspond to the entire hotword; and in response to determining that the initial portion of the audio data and the subsequent portion of the audio data, collectively, do not correspond to the entire hotword, causing the one or more actions of the subset to be reversed. Selecting an additional subset of one or more actions that when performed, reverse the one or more actions of the subset of the one or more actions; and causing the one or more actions of the addition subset to be performed. Prior to receiving the audio data, receiving (i) data indicating the initial portion of the audio data corresponds to the initial portion of the hotword and (ii) data indicating the subset of the actions associated with the hotword. The hotword is a particular term that triggers semantic interpretation of an additional term of one or more terms that follow the particular term.
- The details of one or more embodiments of the subject matter described in this specification are set forth in the accompanying drawings and the description below. Other potential features, aspects, and advantages of the subject matter will become apparent from the description, the drawings, and the claims.
-
FIG. 1 depicts an example system for detecting partial hotwords. -
FIGS. 2A-2F depict swim-lane diagrams of example processes for detecting partial hotwords. -
FIG. 3 depicts an example flowchart for detecting partial hotwords. -
FIG. 4 depicts a computer device and a mobile computer device that may be used to implement the techniques described here. - Like reference symbols in the various drawings indicate like elements.
-
FIG. 1 depicts asystem 100 for detecting partial hotwords. In some examples, thesystem 100 includes anaudio subsystem 102, a partialhotword action initiator 104, ahotword detector 106, a hotword-to-action mapper 108, a hotword-to-action database 110, and anaction engine 112. In some examples, thesystem 100 is a mobile computing device, e.g., amobile computing device 100. In some examples, the mobile computing device includes a smartphone, or tablet-computing device. Themobile computing device 100 can include any audio detection means, e.g., a microphone, for detecting utterances from auser 116. - In some examples, the
user 116 says one or more words that themobile computing device 100 detects. In some examples, the utterance includes one or more hotwords, or partial hotwords, that cause an action to be performed by themobile computing device 100. As depicted in the illustrated example, theuser 116 says “OK Google.” Themobile computing device 100 detects the utterance “OK Google” with theaudio subsystem 102 appropriately receiving audio data of the utterance “OK Google.” - In the illustrated example, the
audio subsystem 102 receives the initial portion of the audio data associated with the utterance “OK” at a time t1. The initial portion of the audio data can include a first few audio frames of the utterance, or a first few hundred milliseconds of audio data associated with the utterance. In some examples, theaudio subsystem 102 processes the utterance to generate waveform data that includes a portion of the utterance, or substantially a whole portion of the utterance. - In some examples, the
audio subsystem 102 appropriately processes the received audio data. For example, theaudio subsystem 102 identifies one or more acoustic features of the initial portion of the audio data. In the illustrated example, theaudio subsystem 102 identifies acoustic features associated with the initial portion of the audio data associated with the utterance “OK.” In some examples, theaudio subsystem 102 obtains a transcription of the initial portion of the audio data associated with the utterance “OK.” In the illustrated example, theaudio subsystem 102 obtains a transcription of the initial portion of the audio data associated with the utterance “OK.” - In some examples, the
audio subsystem 102 provides the processed audio data to the partialhotword action initiator 104. For example, theaudio subsystem 102 provides the processed audio data associated with the utterance “OK” to the partialhotword action initiator 104. In some examples, the processed audio data can include acoustic features associated with the utterance “OK,” a transcription associated with the utterance “OK,” or both. - The partial
hotword action initiator 104 receives the processed audio data from theaudio subsystem 102. For example, the processed audio data can include audio data associated with the utterance “OK,” acoustic features associated with the utterance “OK,” a transcription associated with the utterance “OK,” or any combination thereof. The partialhotword action initiator 104 provides the processed audio data to thehotword detector 106. - The
hotword detector 106 receives the processed audio data from the partialhotword action initiator 104. In the illustrated example, thehotword detector 106 initially receives the processed audio data associated with the utterance “OK,” e.g., an initial portion of the audio data. Thehotword detector 106 determines that the received audio data corresponds to an initial portion of a hotword. Specifically, thehotword detector 106 includes apartial hotword detector 118. Thepartial hotword detector 118 determines that the initial portion of the audio data corresponds to an initial portion of a hotword. In the illustrated example, thepartial hotword detector 118 determines that the initial portion of the audio data associated with the utterance “OK” corresponds to an initial portion of a hotword “OK Google.” In some examples, the initial portion of a hotword includes less than the entire hotword. For example, the initial portion “OK” is less than the entire hotword “OK Google.” - In some examples, the received audio data includes associated acoustic features, e.g., as identified by the
audio subsystem 102. Thepartial hotword detector 118 compares the acoustic features of the initial portion of the audio data associated with the utterance “OK” to acoustic features associated with one or more hotwords stored in a database. Specifically, each hotword is associated with one or more acoustic features, e.g., phonetics of the hotword. A database, or table, stores a mapping between the hotwords and an associated acoustic feature(s). In some examples, a hotword, is associated with two or more acoustic features. In some examples, an acoustic feature is associated with two or more hotwords. - Based on the comparing of acoustic features, the initial portion of the audio data associated with the utterance “OK” is determined to correspond to an initial portion of a hotword stored in the database. For example, it is determined that the acoustic features of the initial portion of the audio data associated with the utterance “OK” corresponds to an initial portion of a hotword “OK Google” based on the comparison of the acoustic features of the utterance “OK” and the acoustic features of the hotword “OK Google.”
- In some examples, the processed audio data includes a transcription, e.g., as obtained by the
audio subsystem 102. Thepartial hotword detector 118 compares the transcription of the initial portion of the audio data associated with the utterance “OK,” to transcriptions associated with hotwords stored in a database. Specifically, a hotword is associated with a transcription. A database, or table, stores a mapping between the hotword and a transcription. - Based on the comparing of transcriptions, the transcription of the initial portion of the audio data associated with the partial utterance “OK” is determined to correspond to an initial portion of a hotword stored in a database. For example, it is determined that the transcription of the initial portion of the audio data associated with the utterance “OK” corresponds to an initial portion of a hotword “OK Google” based on the comparison of the transcription of the utterance “OK” and the transcription of the hotword “OK Google.”
- The
hotword detector 106 provides a result of the determination that the initial portion of the audio data corresponds to the initial portion of a hotword to the partialhotword action initiator 104. Specifically, in the illustrated example, thehotword detector 106 provides the partial hotword “OK,” or a signal associated with the partial hotword “OK,” to the partialhotword action initiator 104. - The partial
hotword action initiator 104 receives the result of the determination from thehotword detector 106. Specifically, in the illustrated example, the partialhotword action initiator 104 receives the partial hotword “OK,” or a signal associated with the partial hotword “OK,” from thehotword detector 106. The signal can include an indication that the initial portion of the audio data associated with the utterance “OK” corresponds to an initial portion of a hotword. In response, the partialhotword action initiator 104 provides the partial hotword “OK,” or the signal associated with the partial hotword “OK,” to the hotword-to-action mapper 108. - The hotword-to-
action mapper 108 receives the result of the determination that the initial portion of the audio data corresponds to the initial portion of the hotword from the partialhotword action initiator 104. Specifically, in the illustrated example, the hotword-to-action mapper 108 receives the partial hotword “OK,” or the signal associated with the partial hotword “OK,” from the partialhotword action initiator 104. The hotword-to-action mapper 108 selects, from among a set of actions that are performed when the entire hotword is detected, a subset of the actions. Specifically, each hotword is associated with one or more actions, e.g., actions that are performed when the entire hotword is detected. A hotword-to-action database 110 stores mapping between hotwords and associated actions. In some examples, a hotword is mapped to two or more actions. In some examples, an action is mapped to two or more hotwords. - In the illustrated example, upon detection of the partial hotword “OK,” the hotword-to-
action mapper 108 identifies a particular set of actions that are associated with the entire hotword “OK Google.” That is, the hotword-to-action mapper 108 is in communication with the hotword-to-action database 110 to identify a mapping between the entire hotword “OK Google” and the particular set of actions from multiple sets of actions that are associated with the entire hotword “OK Google.” The hotword-to-action mapper 108 selects a subset of actions from among the particular set of actions associated with the entire hotword “OK Google.” Specifically, the hotword-to-action mapper 108 selects the subset of actions that are further associated with the partial hotword “OK” of the entire hotword “OK Google.” In some examples, the hotword-to-action mapper 108 identifies the subset of actions that are associated with the partial hotword “OK.” - In some examples, the hotword-to-
action mapper 108 can use multiple criteria for selecting the subset of actions. For example, the hotword-to-action mapper 108 can select actions from the particular set of actions that are not visible to the user. That is, select actions that are not visible to the user that include actions caused to be performed by themobile computing device 116 that are not readably noticeable or detectable by theuser 116, e.g., visually or audible detectable by theuser 116. For example, the actions can include actions that are not shown on a user interface of themobile computing device 100, or actions that do not make noise by themobile computing device 100. In some examples, the selected actions can include actions that are performed in a background computing environment of themobile computing device 100. In the illustrated example, the subset of actions include an action of establishing a network connection, e.g., with a third-party computing server or a back-end computing server. In some examples, the selected actions can include actions that have no lasting or permanent effects, i.e., are reversible, on the mobile computing device - The hotword-to-
action mapper 108 provides data identifying the subset of actions to the partialhotword action interior 104. Specifically, the hotword-to-action mapper 108 provides data identifying the subset of actions associated with the hotword “OK Google” to the partialhotword action initiator 104. - The partial
hotword action initiator 104 receives the data identifying the subset of actions from the hotword-to-action mapper 108, and in response, provides the data identifying the subset of actions to theaction engine 112. Specifically, by providing the data identifying the subset of actions to theaction engine 112, the partialhotword action initiator 104 causes the subset of actions to be performed. - The
action engine 112 receives the data identifying the subset of actions from the partialhotword action initiator 104. In the illustrated example, theaction engine 112 receives the data identifying the subset of actions associated with the initial portion of the hotword “OK Google,” as selected by the hotword-to-action mapper 108. - Specifically, the subset of actions that are associated with the partial hotword “OK” of the entire hotword “OK Google” are performed at the time t1. The
action engine 112 causes an action of establishing a network connection to be performed, e.g., by the operating system executing on themobile computing device 100. - In some examples, causing the subset of actions to be performed includes transmitting an interrupt signal to the operating system executing on the
mobile computing device 100. In some examples, the interrupt signal causes the operating system to initialize a camera functionality of themobile computing device 100. In some examples, the interrupt signal causes the operating stem to activate themobile computing device 100 from a sleep state. That is, that state of themobile computing device 100 is changed from a sleep state, or an “off” state, to a wake state, or an “on” state. In some examples, the interrupt signal causes the operating system to preload an application stored on themobile computing device 100 that is associated with the hotword. That is, the application can be preloaded into a memory of themobile computing device 100. - In some further implementations, after receiving the initial portion of the audio data, the
audio subsystem 102 receives a subsequent portion of the audio data. For example, theaudio subsystem 102 receives the subsequent portion of the detected utterance, e.g., subsequent to the initial portion of the audio data. In the illustrated example, theaudio subsystem 102 receives the subsequent portion of the audio data associated with the utterance “Google” at a time t2. Theaudio subsystem 102 appropriately processes the received audio data. In some examples, theaudio subsystem 102 receives a whole portion of the audio, including the initial portion and the subsequent portion. - In some examples, the hotword is a particular term that triggers semantic interpretation of an additional term of one or more terms that follow the particular term. For example, by the initial portion of the audio data associated with the utterance “OK” corresponding to an initial portion of a hotword, the
audio subsystem 102 provides a semantic interpretation of the subsequent portion of the audio data associated with the utterance “Google.” - In some examples, the
audio subsystem 102 provides the processed audio data associated with the entire utterance to the partialhotword action initiator 104. For example, theaudio subsystem 102 provides the processed audio data associated with the utterance “OK Google” to the partialhotword action initiator 104. In some examples, the processed audio data can include acoustic features associated with the utterance “OK Google,” a transcription associated with the utterance “OK Google,” or both. - The partial
hotword action initiator 104 receives the processed audio data from theaudio subsystem 102. For example, the processed audio data can include the audio data associated with the utterance “OK Google,” acoustic features associated with the audio data associated with the utterance “OK Google,” a transcription associated with the audio data associated with the utterance “OK Google,” or any combination thereof. The partialhotword action initiator 104 provides the processed audio data to thehotword detector 106. - The
hotword detector 106 receives the processed audio data from the partialhotword action initiator 104. In the illustrated example, thehotword detector 106 receives the processed audio data associated with the initial portion of the audio associated with the utterance “OK” and the subsequent portion of the audio data associated with the utterance “Google.” In other words, thehotword detector 106 receives the audio data associated with the entire utterance “OK Google.” In the illustrated example, thehotword detector 106 determines that the initial and the subsequent portion of the audio data, collectively, correspond to the entire hotword “OK Google.” - The
hotword detector 106 provides a result of the determination that the initial portion and the subsequent portion of the audio data associated with the utterance “OK Google” collectively correspond to the entire hotword to the partialhotword action initiator 104. Specifically, in the illustrated example, thehotword detector 106 provides the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” to the partialhotword action initiator 104. The signal can include an indication that the initial portion and the subsequent portion of the audio data, collectively, correspond to an entire hotword. - The partial
hotword action initiator 104 receives the result of the determination from thehotword detector 106. Specifically, in the illustrated example, the partialhotword action initiator 104 receives the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” from thehotword detector 106. In response, the partialhotword action initiator 104 provides the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” to the hotword-to-action mapper 108. - The hotword-to-
action mapper 108 receives the result, e.g., a signal, of the determination that the initial portion and the subsequent portion of the audio data associated with the utterance “OK Google” collectively correspond to the entire hotword from the partialhotword action initiator 104. Specifically, in the illustrated example, the hotword-to-action mapper 108 receives the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” from the partialhotword action initiator 104. The hotword-to-action mapper 108 selects, from among a set of actions that are performed when the entire hotword is detected, an additional subset of the actions. - In the illustrated example, upon receipt of the entire hotword “OK Google,” or the signal associated with the entire hotword “OK Google,” the hotword-to-
action mapper 108 identifies a particular set of actions that are associated with the entire hotword “OK Google.” That is, the hotword-to-action mapper 108 is in communication with the hotword-to-action database 110 to identify a mapping between the entire hotword “OK Google” and the particular set of actions from multiple sets of actions. The hotword-to-action mapper 108 selects an additional subset of actions from among the particular set of actions associated with the entire hotword “OK Google.” In some examples, the set of actions associated with the entire hotword “OK Google” includes the subset of actions and the additional subset of actions. In some examples, the additional subset of actions includes the subset of actions. In some examples, the additional subset of actions includes one or more actions of the subset of actions. For example, upon detection of the entire hotword “OK Google,” each action of the subset of actions may have not been fully performed by theaction engine 112. Thus, any unperformed actions associated with the subset of actions can further be included by the additional subset of actions. - The hotword-to-
action mapper 108 provides data identifying the additional subset of actions to the partialhotword action initiator 104. That is, the hotword-to-action mapper 108 provides data identifying the additional subset of actions associated with the detection of the entire hotword “OK Google” to the partialhotword action initiator 104. - The partial
hotword action initiator 104 receives the data identifying the additional subset of actions from the hotword-to-action mapper 108, and in response, provides the data identifying the additional subset of actions to theaction engine 112. Specifically, by providing the data identifying the additional subset of actions to theaction engine 112, the partialhotword action initiator 104 causes the additional subset of actions to be performed. - The
action engine 112 receives the data identifying the additional subset of actions from the partialhotword action initiator 104. In the illustrated example, theaction engine 112 receives the data identifying the additional subset of actions associated with the detection of the entire hotword, as selected by the hotword-to-action mapper 108. Specifically, the additional subset of actions that are associated with the entire hotword “OK Google” are performed at the time t2. In response to receiving the additional subset of actions, theaction engine 112 causes an action of turning a display, or screen, of themobile computing device 100 to be in an “on” state. In some examples, in response to receiving the additional subset of actions, theaction engine 112 causes an action of displaying a user interface. In some examples, the set of actions associated with the detection of the partial hotword “OK” and the additional set of actions associated with the detection of the entire hotword “OK Google” are caused to be performed by theaction engine 112 in parallel, or at substantially the same time. - In some further implementations, before receiving the audio data, additional data is received (i) indicating that the initial portion of the audio data corresponds to the initial portion of the hotword and additional data (ii) indicating the subset of the actions associated with the hotword. For example, prior to receiving the audio data “OK Google” from the
user 116, themobile computing device 100 is “trained,” e.g., receives the additional data, such that thepartial hotword detector 118 is able to determine whether an initial portion of the audio data, e.g., the “OK” utterance, corresponds to an initial portion of a hotword, e.g., “OK Google.” Additionally, for example, themobile computing device 100 receives the additional data such that the hotword-to-action-mapper 108 and the hotword-to-action database 110 are able to identify a subset of actions associated with the hotword “OK Google.” That is, the hotword-to-action-mapper 108 receives data such that the hotword-to-action database 110 maps associations between hotwords, e.g., “OK Google,” and actions, e.g., establishing network connection actions and/or waking themobile computing device 100. -
FIG. 2 illustrates a swim-lane diagram of interactions between anaudio subsystem 295, a partialhotword action initiator 296, ahotword detector 297, a hotword-to-action mapper 298, and anaction engine 299. In some examples, theaudio subsystem 295 can include theaudio subsystem 102 ofFIG. 1 ; the partialhotword action initiator 296 can include thepartial hotword initiator 104 ofFIG. 1 ; thehotword detector 297 can include thehotword detector 106, thepartial hotword detector 118, or both, ofFIG. 1 ; the hotword-to-action mapper 298 can include the hotword-to-action mapper 108 ofFIG. 1 ; and theaction engine 299 can include theaction engine 112 ofFIG. 1 . Specifically, in the illustrated example, a user, e.g., theuser 116, provides the utterance “OK computer I mean OK Google call Mom” to a mobile computing device, e.g., themobile computing device 100. - As illustrated in
FIG. 2A , atstep 201, theaudio subsystem 295 receives and appropriately processes the partial utterance “OK.” Atstep 202, the partialhotword action initiator 296 receives the processed partial utterance “OK” and forwards the same to thehotword detector 297. Atstep 203, thehotword detector 297 determines that the partial utterance “OK” corresponds to, at least, an initial portion of the hotword “OK Google.” In some examples, the partial utterance “OK” can correspond to an initial portion of two or more hotwords. Atstep 204, thehotword detector 297 provides the determination, or result, to the partialhotword action initiator 296. For example, thepartial hotword detector 296 determines that the partial utterance “OK” correspond to an initial portion of a hotword “OK Google.” Atstep 205, the partialhotword action initiator 296 receives the determination, or result, and atstep 206, in response, triggers the hotword-to-action mapper 298. For example, in response to the partial utterance “OK” corresponding to an initial portion of a hotword, the partialhotword action initiator 296 triggers the hotword-to-action-mapper 298 by providing the partial hotword “OK,” or a signal associated with the partial hotword “OK,” to the hotword-to-action initiator 298. - At
step 207, the hotword-to-action mapper 298 maps the partial hotword “OK” of the entire hotword “OK Google” to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the partial hotword “OK” of the hotword “OK Google” to a network connection action, e.g., initializing or opening a network connection. Atstep 208, the hotword-to-action mapper 298 provides information associated with the network connection action to the partialhotword action initiator 296. Atstep 209, the partialhotword action initiator 296 receives the information associated with the network connection action. Atstep 210, the partialhotword action initiator 296 causes the network connection action to be performed. That is, the partialhotword action initiator 296 provides the information associated with the network connection action to theaction engine 299. Atstep 211, theaction engine 299 appropriately processes the network connection action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the network connection action. - As illustrated in
FIG. 2B , atstep 215, theaudio subsystem 295 receives and appropriately processes the partial utterance “computer.” Atstep 216, the partialhotword action initiator 296 receives the processed partial utterance “computer” and forwards the same to thepartial hotword detector 118. Atstep 217, thehotword detector 297 determines that the entire utterance “OK computer” does not correspond to, at least, the entire hotword “OK Google,” or any other hotword. Specifically, in the illustrated example, thehotword detector 297 determines that the initial portion and the subsequent portion of the utterance “OK computer” does not correspond to an entire hotword. - In some examples, the processed audio data includes associated acoustic features, e.g., as identified by the
audio subsystem 102. Thehotword detector 297 can compare the acoustic features of the audio data associated with the entire utterance “OK computer” to acoustic features associated with one or more hotwords stored in a database. Based on the comparing of acoustic features, the audio data associated with the entire utterance “OK computer” is determined not to correspond to a hotword stored in the database. - In some examples, the processed audio data includes a transcription, e.g., as obtained by the
audio subsystem 295. Thehotword detector 297 can compare the transcription of the audio data associated with the entire utterance “OK computer” to transcriptions associated with hotwords stored in a database. Based on the comparing of transcriptions, the audio data associated with the entire utterance “OK computer” is determined not to correspond to a hotword stored in a database. - At
step 218, thehotword detector 297 provides the determination, or result, to the partialhotword action initiator 296. For example, thehotword detector 297 determines that the entire utterance “OK computer” does not correspond to a hotword. Atstep 219, the partialhotword action initiator 296 receives the determination, or result, and at step 220, in response, triggers the hotword-to-action mapper 298. For example, in response to the utterance “OK computer” not corresponding to a hotword, the partialhotword action initiator 297 triggers the hotword-to-action-mapper 298. Atstep 221, the hotword-to-action mapper 298 selects an additional subset of actions that when performed, cause the open network connection action to be reversed, or cancelled. For example, each particular action corresponding to a hotword can further be associated with one or more additional actions that when selected, reverse the particular action that was previously performed. For example, the open network connection action, as performed atstep 211, can be associated with a close network connection action such that when the hotword “OK Google” is not detected, e.g., after detecting the partial hotword “OK,” the open network connection action is reversed. In some examples, each particular action can be associated with two or more additional actions that reverse the particular action, e.g., negate the particular action. - At
step 222, the hotword-to-action mapper 298 provides information associated with the close network connection action to the partialhotword action initiator 296. Atstep 223, the partialhotword action initiator 296 receives the information associated with the close network connection action. Atstep 224, the partialhotword action initiator 296 causes the close network connection action to be performed. That is, the partialhotword action initiator 296 provides the information associated with the close network connection action to theaction engine 299. Atstep 225, theaction engine 299 appropriately processes the close network connection action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the close network connection action. - As illustrated at
FIG. 2C , atstep 230, theaudio subsystem 295 receives and appropriately processes the utterance “I mean.” Atstep 231, the partialhotword action initiator 296 receives the processed utterance “I mean” and forwards the same to thehotword detector 297. Atstep 232, thehotword detector 297 determines that the utterance “I mean” does not corresponds to, at least, an initial portion of a hotword or an entire hotword. Atstep 233, thehotword detector 297 provides the determination, or result, to the partialhotword action initiator 296. Atstep 234, the partialhotword action initiator 296 receives the determination, or result, and, in response to the utterance “I mean” not corresponding to an initial portion of a hotword or an entire hotword, takes no further action. - At
step 235, theaudio subsystem 295 receives and appropriately processes the partial utterance “OK.” Atstep 236, the partialhotword action initiator 295 receives the processed partial utterance “OK” and forwards the same to thehotword detector 297. Atstep 237, thehotword detector 297 determines that the partial utterance “OK” corresponds to, at least, an initial portion of the hotword “OK Google.” Atstep 238, thehotword detector 297 provides the determination, or result, to the partialhotword action initiator 296. For example, thehotword detector 297 determines that the partial utterance “OK” correspond to an initial portion of a hotword “OK Google.” Atstep 239, the partialhotword action initiator 296 receives the determination, or result, and atstep 240, in response, triggers the hotword-to-action mapper 298. For example, in response to the partial utterance “OK” corresponding to an initial portion of a hotword, the partialhotword action initiator 296 triggers the hotword-to-action-mapper 298 by providing the partial hotword “OK,” or a signal associated with the partial hotword “OK,” to the hotword-to-action mapper 298. - At
step 241, the hotword-to-action mapper 298 maps the partial hotword “OK” to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the partial hotword “OK” of the entire hotword “OK Google” to a network connection action, e.g., initializing or opening a network connection. Atstep 242, the hotword-to-action mapper 298 provides information associated with the network connection action to the partialhotword action initiator 296. Atstep 243, the partialhotword action initiator 296 receives information associated with the network connection action. Atstep 244, the partialhotword action initiator 296 causes the network connection action to be performed. That is, the partialhotword action initiator 296 provides the information associated with the network connection action to theaction engine 299. Atstep 245, theaction engine 299 appropriately processes the network connection action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the network connection action. - As illustrated at
FIG. 2D , atstep 250, theaudio subsystem 295 receives and appropriately processes the partial utterance “Google.” Atstep 251, the partialhotword action initiator 296 receives the processed partial utterance “Google” and forwards the same to thehotword detector 297. Atstep 252, thehotword detector 297 determines that the utterance “OK Google” corresponds to, at least, a hotword “OK Google.” Atstep 253, thehotword detector 297 provides the determination, or result, to the partialhotword action initiator 296. For example, thepartial hotword detector 297 determines that the initial utterance “OK” and the subsequent utterance “Google,” collectively correspond to the hotword “OK Google.” Atstep 254, the partialhotword action initiator 296 receives the determination, or result, and atstep 255, in response, triggers the hotword-to-action mapper 298. For example, in response to the initial utterance “OK” and the subsequent utterance “Google,” collectively, corresponding to an entire hotword, the partialhotword action initiator 296 triggers the hotword-to-action-mapper 298 by providing the entire hotword “OK Google,” or a signal associated with the entire hotword “OK Google,” to the hotword-to-action mapper 298. - At
step 256, the hotword-to-action mapper 298 maps the hotword to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the hotword “OK Google” to a wake mobile device action, e.g., waking the mobile computing device from a sleep state, or “off state,” to a wake state, or an “on” state. Atstep 257, the hotword-to-action mapper 298 provides information associated with the wake mobile device action to the partialhotword action initiator 296. Atstep 258, the partialhotword action initiator 296 receives information associated with the wake mobile device action. Atstep 259, the partialhotword action initiator 296 causes the wake mobile device action to be performed. That is, the partialhotword action initiator 296 provides the information associated with the wake mobile device action to theaction engine 299. Atstep 260, theaction engine 299 appropriately processes the wake mobile device action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the wake mobile device action. - As illustrated at
FIG. 2E , atstep 265, theaudio subsystem 295 receives and appropriately processes the partial utterance “Call.” Atstep 266, the partialhotword action initiator 296 receives the processed partial utterance “Call” and forwards the same to thehotword detector 297. Atstep 267, thehotword detector 297 determines that the partial utterance “Call” corresponds to, at least, an initial portion of a hotword. Atstep 268, thehotword detector 297 provides the determination, or result, to the partialhotword action initiator 296. For example, thehotword detector 297 determines that the partial utterance “Call” correspond to an initial portion of a hotword. Atstep 269, the partialhotword action initiator 296 receives the determination, or result, and atstep 270, in response, triggers the hotword-to-action mapper 298. For example, in response to the partial utterance “Call” corresponding to an initial portion of a hotword, the partialhotword action initiator 296 triggers the hotword-to-action-mapper 298 by providing the partial hotword “Call” to the hotword-to-action mapper 108. - At
step 271, the hotword-to-action mapper 298 maps the partial hotword of the hotword to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the partial hotword “Call” to a launch telephone application action, e.g., preloading of an application on a mobile computing device. Atstep 272, the hotword-to-action mapper 298 provides information associated with the launch telephone application action to the partialhotword action initiator 296. Atstep 273, the partialhotword action initiator 296 receives information associated with the launch telephone application action. Atstep 274, the partialhotword action initiator 296 causes the launch telephone application action to be performed. That is, the partialhotword action initiator 296 provides the information associated with the launch telephone application action to theaction engine 299. Atstep 275, theaction engine 299 appropriately processes the launch telephone application action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the launch telephone application action. - As illustrated at
FIG. 2F , atstep 280, theaudio subsystem 295 receives and appropriately processes the partial utterance “Mom.” Atstep 281, the partialhotword action initiator 296 receives the processed partial utterance “Mom” and forwards the same to thehotword detector 297. Atstep 282, thehotword detector 297 determines that the initial utterance “Call” and the subsequent utterance “Mom,” collectively, correspond to, at least, the hotword “Call Mom.” Atstep 283, thehotword detector 297 provides the determination, or result, to the partialhotword action initiator 296. For example, thehotword detector 297 determines that the initial utterance “Call” and the subsequent utterance “Mom,” collectively, correspond to an entire hotword. Atstep 284, the partialhotword action initiator 296 receives the determination, or result, and atstep 285, in response, triggers the hotword-to-action mapper 298. For example, in response to the initial utterance “Call” and the subsequent utterance “Mom,” collectively, corresponding to an entire hotword, the partialhotword action initiator 296 triggers the hotword-to-action-mapper 298 by providing the entire hotword “Call Mom” to the hotword-to-action mapper 298. - At
step 286, the hotword-to-action mapper 298 maps the entire hotword “Call Mom” to an action, e.g., utilizing a database. For example, the hotword-to-action mapper 298 maps the entire hotword “Call Mom” to a contact assigned with the utterance “Mom.” The user may have previously associated the utterance “Mom” with a contact stored by a mobile computing device. Atstep 287, the hotword-to-action mapper 298 provides information associated with the place call to “Mom” action to the partialhotword action initiator 296. Atstep 288, the partialhotword action initiator 296 receives information associated with the place call to “Mom” action. For example, the information can include contact information associated with a contact “Mom.” Atstep 289, the partialhotword action initiator 296 causes the call to be placed to “Mom” action to be performed. That is, the partialhotword action initiator 296 provides the information associated with the call to be placed to “Mom” action to theaction engine 299. Atstep 290, theaction engine 299 appropriately processes the call to be placed to “Mom” action information, including transmitting an interrupt signal to an operating system executing on a mobile computing device to perform the call to be placed to “Mom” action. -
FIG. 3 depicts a flowchart of anexample process 300 for identifying partial hotwords. Theexample process 300 can be executed using one or more computing devices. For example, theaudio subsystem 102, the partialhotword action initiator 104, thehotword detector 106, the hotword toaction mapper 108, the hotword-to-action database 110, theaction engine 112, and thepartial hotword detector 118 can be used to execute theexample process 300. - Audio data is received (302). For example, the
audio subsystem 102 receives the audio data of an utterance “OK Google” from the mobile computing device 114. An initial portion of the audio data is determined to correspond to an initial portion of a hotword (304). For example, thehotword detector 106, thepartial hotword detector 118, or both, determine that the initial portion “OK” of the audio data “OK Google” corresponds to an initial portion of a hotword. In response to determining that the initial portion of the audio data corresponds to the initial portion of the hotword, a subset of one or more actions are selected from among a set of one or more actions that are performed when the entire hotword is detected (306). For example, the hotword-to-action mapper 108 identifies a particular set of actions that are associated with the entire hotword “OK Google.” The hotword-to-action mapper 108 selects the subset of actions that are further associated with the partial hotword “OK” of the entire hotword “OK Google.” One or more actions of the subset are caused to be performed (308). For example, theaction engine 112 receives the subset of actions associated with the entire hotword “OK Google” that are caused to be performed. -
FIG. 4 shows an example of ageneric computer device 400 and a genericmobile computer device 450, which may be used with the techniques described here.Computing device 400 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers.Computing device 450 is intended to represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed in this document. -
Computing device 400 includes aprocessor 402,memory 404, astorage device 406, a high-speed interface 408 connecting tomemory 404 and high-speed expansion ports 410, and alow speed interface 412 connecting tolow speed bus 414 andstorage device 406. Each of thecomponents processor 402 may process instructions for execution within thecomputing device 400, including instructions stored in thememory 404 or on thestorage device 406 to display graphical information for a GUI on an external input/output device, such asdisplay 416 coupled tohigh speed interface 408. In other implementations, multiple processors and/or multiple buses may be used, as appropriate, along with multiple memories and types of memory. Also,multiple computing devices 400 may be connected, with each device providing portions of the necessary operations (e.g., as a server bank, a group of blade servers, or a multi-processor system). - The
memory 404 stores information within thecomputing device 400. In one implementation, thememory 404 is a volatile memory unit or units. In another implementation, thememory 404 is a non-volatile memory unit or units. Thememory 404 may also be another form of computer-readable medium, such as a magnetic or optical disk. - The
storage device 406 is capable of providing mass storage for thecomputing device 400. In one implementation, thestorage device 406 may be or contain a computer-readable medium, such as a floppy disk device, a hard disk device, an optical disk device, or a tape device, a flash memory or other similar solid state memory device, or an array of devices, including devices in a storage area network or other configurations. A computer program product may be tangibly embodied in an information carrier. The computer program product may also contain instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer- or machine-readable medium, such as thememory 404, thestorage device 406, or a memory onprocessor 402. - The
high speed controller 408 manages bandwidth-intensive operations for thecomputing device 400, while thelow speed controller 412 manages lower bandwidth-intensive operations. Such allocation of functions is exemplary only. In one implementation, the high-speed controller 408 is coupled tomemory 404, display 416 (e.g., through a graphics processor or accelerator), and to high-speed expansion ports 410, which may accept various expansion cards (not shown). In the implementation, low-speed controller 412 is coupled tostorage device 406 and low-speed expansion port 414. The low-speed expansion port, which may include various communication ports (e.g., USB, Bluetooth, Ethernet, wireless Ethernet) may be coupled to one or more input/output devices, such as a keyboard, a pointing device, a scanner, or a networking device such as a switch or router, e.g., through a network adapter. - The
computing device 400 may be implemented in a number of different forms, as shown in the figure. For example, it may be implemented as astandard server 420, or multiple times in a group of such servers. It may also be implemented as part of arack server system 424. In addition, it may be implemented in a personal computer such as alaptop computer 422. Alternatively, components fromcomputing device 400 may be combined with other components in a mobile device (not shown), such asdevice 450. Each of such devices may contain one or more ofcomputing device multiple computing devices -
Computing device 450 includes aprocessor 452,memory 464, an input/output device such as adisplay 454, a communication interface 466, and atransceiver 468, among other components. Thedevice 450 may also be provided with a storage device, such as a microdrive or other device, to provide additional storage. Each of thecomponents - The
processor 452 may execute instructions within the computing device 640, including instructions stored in thememory 464. The processor may be implemented as a chipset of chips that include separate and multiple analog and digital processors. The processor may provide, for example, for coordination of the other components of thedevice 450, such as control of user interfaces, applications run bydevice 450, and wireless communication bydevice 450. -
Processor 452 may communicate with a user through control interface 648 anddisplay interface 456 coupled to adisplay 454. Thedisplay 454 may be, for example, a TFT LCD (Thin-Film-Transistor Liquid Crystal Display) or an OLED (Organic Light Emitting Diode) display, or other appropriate display technology. Thedisplay interface 456 may comprise appropriate circuitry for driving thedisplay 454 to present graphical and other information to a user. Thecontrol interface 458 may receive commands from a user and convert them for submission to theprocessor 452. In addition, anexternal interface 462 may be provide in communication withprocessor 452, so as to enable near area communication ofdevice 450 with other devices.External interface 462 may provide, for example, for wired communication in some implementations, or for wireless communication in other implementations, and multiple interfaces may also be used. - The
memory 464 stores information within thecomputing device 450. Thememory 464 may be implemented as one or more of a computer-readable medium or media, a volatile memory unit or units, or a non-volatile memory unit or units.Expansion memory 454 may also be provided and connected todevice 450 throughexpansion interface 452, which may include, for example, a SIMM (Single In Line - Memory Module) card interface.
Such expansion memory 454 may provide extra storage space fordevice 450, or may also store applications or other information fordevice 450. Specifically,expansion memory 454 may include instructions to carry out or supplement the processes described above, and may include secure information also. Thus, for example,expansion memory 454 may be provide as a security module fordevice 450, and may be programmed with instructions that permit secure use ofdevice 450. In addition, secure applications may be provided via the SIMM cards, along with additional information, such as placing identifying information on the SIMM card in a non-hackable manner. - The memory may include, for example, flash memory and/or NVRAM memory, as discussed below. In one implementation, a computer program product is tangibly embodied in an information carrier. The computer program product contains instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer- or machine-readable medium, such as the
memory 464,expansion memory 454, memory onprocessor 452, or a propagated signal that may be received, for example, overtransceiver 468 orexternal interface 462. -
Device 450 may communicate wirelessly through communication interface 466, which may include digital signal processing circuitry where necessary. Communication interface 466 may provide for communications under various modes or protocols, such as GSM voice calls, SMS, EMS, or MMS messaging, CDMA, TDMA, PDC, WCDMA, CDMA2000, or GPRS, among others. Such communication may occur, for example, through radio-frequency transceiver 468. In addition, short-range communication may occur, such as using a Bluetooth, WiFi, or other such transceiver (not shown). In addition, GPS (Global Positioning System)receiver module 450 may provide additional navigation- and location-related wireless data todevice 450, which may be used as appropriate by applications running ondevice 450. -
Device 450 may also communicate audibly usingaudio codec 460, which may receive spoken information from a user and convert it to usable digital information.Audio codec 460 may likewise generate audible sound for a user, such as through a speaker, e.g., in a handset ofdevice 450. Such sound may include sound from voice telephone calls, may include recorded sound (e.g., voice messages, music files, etc.) and may also include sound generated by applications operating ondevice 450. - The
computing device 450 may be implemented in a number of different forms, as shown in the figure. For example, it may be implemented as acellular telephone 480. It may also be implemented as part of asmartphone 482, personal digital assistant, or other similar mobile device. - Various implementations of the systems and techniques described here may be realized in digital electronic circuitry, integrated circuitry, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various implementations may include implementation in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.
- These computer programs (also known as programs, software, software applications or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms “machine-readable medium” “computer-readable medium” refers to any computer program product, apparatus and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term “machine-readable signal” refers to any signal used to provide machine instructions and/or data to a programmable processor.
- To provide for interaction with a user, the systems and techniques described here may be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user may provide input to the computer. Other kinds of devices may be used to provide for interaction with a user as well; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
- The systems and techniques described here may be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a client computer having a graphical user interface or a Web browser through which a user may interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (“LAN”), a wide area network (“WAN”), and the Internet.
- The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
- While this disclosure includes some specifics, these should not be construed as limitations on the scope of the disclosure or of what may be claimed, but rather as descriptions of features of example implementations of the disclosure. Certain features that are described in this disclosure in the context of separate implementations can also be provided in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be provided in multiple implementations separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
- Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the implementations described above should not be understood as requiring such separation in all implementations, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
- Thus, particular implementations of the present disclosure have been described. Other implementations are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order and still achieve desirable results. A number of implementations have been described. Nevertheless, it will be understood that various modifications may be made without departing from the spirit and scope of the disclosure. For example, various forms of the flows shown above may be used, with steps re-ordered, added, or removed. Accordingly, other implementations are within the scope of the following claims.
Claims (20)
Priority Applications (11)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/220,781 US9330663B2 (en) | 2013-12-04 | 2014-03-20 | Initiating actions based on partial hotwords |
CN201480066328.1A CN105793921B (en) | 2013-12-04 | 2014-03-21 | Initiating actions based on partial hotwords |
PCT/US2014/031475 WO2015084425A1 (en) | 2013-12-04 | 2014-03-21 | Initiating actions based on partial hotwords |
EP14723220.1A EP3078021B1 (en) | 2013-12-04 | 2014-03-21 | Initiating actions based on partial hotwords |
EP18211411.6A EP3483876A1 (en) | 2013-12-04 | 2014-03-21 | Initiating actions based on partial hotwords |
CN201911377903.0A CN111524510B (en) | 2013-12-04 | 2014-03-21 | Initiating actions based on partial hotwords |
US14/990,462 US9443512B2 (en) | 2013-12-04 | 2016-01-07 | Initiating actions based on partial hotwords |
US14/991,092 US9502026B2 (en) | 2013-12-04 | 2016-01-08 | Initiating actions based on partial hotwords |
US15/191,046 US9508342B2 (en) | 2013-12-04 | 2016-06-23 | Initiating actions based on partial hotwords |
US15/299,853 US9620114B2 (en) | 2013-12-04 | 2016-10-21 | Initiating actions based on partial hotwords |
US15/466,979 US9805719B2 (en) | 2013-12-04 | 2017-03-23 | Initiating actions based on partial hotwords |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/096,359 US8768712B1 (en) | 2013-12-04 | 2013-12-04 | Initiating actions based on partial hotwords |
US14/220,781 US9330663B2 (en) | 2013-12-04 | 2014-03-20 | Initiating actions based on partial hotwords |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/096,359 Continuation US8768712B1 (en) | 2013-12-04 | 2013-12-04 | Initiating actions based on partial hotwords |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/990,462 Division US9443512B2 (en) | 2013-12-04 | 2016-01-07 | Initiating actions based on partial hotwords |
Publications (2)
Publication Number | Publication Date |
---|---|
US20150154954A1 true US20150154954A1 (en) | 2015-06-04 |
US9330663B2 US9330663B2 (en) | 2016-05-03 |
Family
ID=50982188
Family Applications (7)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/096,359 Active US8768712B1 (en) | 2013-12-04 | 2013-12-04 | Initiating actions based on partial hotwords |
US14/220,781 Active 2034-01-15 US9330663B2 (en) | 2013-12-04 | 2014-03-20 | Initiating actions based on partial hotwords |
US14/990,462 Active US9443512B2 (en) | 2013-12-04 | 2016-01-07 | Initiating actions based on partial hotwords |
US14/991,092 Active US9502026B2 (en) | 2013-12-04 | 2016-01-08 | Initiating actions based on partial hotwords |
US15/191,046 Active US9508342B2 (en) | 2013-12-04 | 2016-06-23 | Initiating actions based on partial hotwords |
US15/299,853 Active US9620114B2 (en) | 2013-12-04 | 2016-10-21 | Initiating actions based on partial hotwords |
US15/466,979 Active US9805719B2 (en) | 2013-12-04 | 2017-03-23 | Initiating actions based on partial hotwords |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/096,359 Active US8768712B1 (en) | 2013-12-04 | 2013-12-04 | Initiating actions based on partial hotwords |
Family Applications After (5)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/990,462 Active US9443512B2 (en) | 2013-12-04 | 2016-01-07 | Initiating actions based on partial hotwords |
US14/991,092 Active US9502026B2 (en) | 2013-12-04 | 2016-01-08 | Initiating actions based on partial hotwords |
US15/191,046 Active US9508342B2 (en) | 2013-12-04 | 2016-06-23 | Initiating actions based on partial hotwords |
US15/299,853 Active US9620114B2 (en) | 2013-12-04 | 2016-10-21 | Initiating actions based on partial hotwords |
US15/466,979 Active US9805719B2 (en) | 2013-12-04 | 2017-03-23 | Initiating actions based on partial hotwords |
Country Status (4)
Country | Link |
---|---|
US (7) | US8768712B1 (en) |
EP (2) | EP3078021B1 (en) |
CN (2) | CN111524510B (en) |
WO (1) | WO2015084425A1 (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160171975A1 (en) * | 2014-12-11 | 2016-06-16 | Mediatek Inc. | Voice wakeup detecting device and method |
US9542941B1 (en) * | 2015-10-01 | 2017-01-10 | Lenovo (Singapore) Pte. Ltd. | Situationally suspending wakeup word to enable voice command input |
US9775113B2 (en) | 2014-12-11 | 2017-09-26 | Mediatek Inc. | Voice wakeup detecting device with digital microphone and associated method |
US20180121161A1 (en) * | 2016-10-28 | 2018-05-03 | Kyocera Corporation | Electronic device, control method, and storage medium |
WO2018151772A1 (en) * | 2017-02-14 | 2018-08-23 | Google Llc | Server side hotwording |
US10102856B2 (en) * | 2017-01-20 | 2018-10-16 | Essential Products, Inc. | Assistant device with active and passive experience modes |
US10438583B2 (en) * | 2016-07-20 | 2019-10-08 | Lenovo (Singapore) Pte. Ltd. | Natural language voice assistant |
US10621992B2 (en) | 2016-07-22 | 2020-04-14 | Lenovo (Singapore) Pte. Ltd. | Activating voice assistant based on at least one of user proximity and context |
US10664533B2 (en) | 2017-05-24 | 2020-05-26 | Lenovo (Singapore) Pte. Ltd. | Systems and methods to determine response cue for digital assistant based on context |
US10769189B2 (en) | 2015-11-13 | 2020-09-08 | Microsoft Technology Licensing, Llc | Computer speech recognition and semantic understanding from activity patterns |
EP3751561A3 (en) * | 2015-10-16 | 2020-12-30 | Google LLC | Hotword recognition |
US10984783B2 (en) * | 2019-03-27 | 2021-04-20 | Intel Corporation | Spoken keyword detection based utterance-level wake on intent system |
US20210134272A1 (en) * | 2018-07-20 | 2021-05-06 | Sony Corporation | Information processing device, information processing system, information processing method, and program |
US11429883B2 (en) | 2015-11-13 | 2022-08-30 | Microsoft Technology Licensing, Llc | Enhanced computer experience from activity prediction |
EP4057278A1 (en) * | 2021-03-10 | 2022-09-14 | Comcast Cable Communications, LLC | Systems and methods for improved speech and command detection |
US20230019595A1 (en) * | 2020-02-07 | 2023-01-19 | Sonos, Inc. | Localized Wakeword Verification |
US11961519B2 (en) * | 2022-04-18 | 2024-04-16 | Sonos, Inc. | Localized wakeword verification |
Families Citing this family (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9349046B2 (en) | 2009-02-10 | 2016-05-24 | Kofax, Inc. | Smart optical input/output (I/O) extension for context-dependent workflows |
US9536528B2 (en) | 2012-07-03 | 2017-01-03 | Google Inc. | Determining hotword suitability |
US10381002B2 (en) * | 2012-10-30 | 2019-08-13 | Google Technology Holdings LLC | Voice control user interface during low-power mode |
US9584642B2 (en) * | 2013-03-12 | 2017-02-28 | Google Technology Holdings LLC | Apparatus with adaptive acoustic echo control for speakerphone mode |
US10304465B2 (en) * | 2012-10-30 | 2019-05-28 | Google Technology Holdings LLC | Voice control user interface for low power mode |
US10373615B2 (en) * | 2012-10-30 | 2019-08-06 | Google Technology Holdings LLC | Voice control user interface during low power mode |
GB2524222B (en) * | 2013-12-18 | 2018-07-18 | Cirrus Logic Int Semiconductor Ltd | Activating speech processing |
US9946985B2 (en) * | 2014-04-15 | 2018-04-17 | Kofax, Inc. | Touchless mobile applications and context-sensitive workflows |
US9697828B1 (en) * | 2014-06-20 | 2017-07-04 | Amazon Technologies, Inc. | Keyword detection modeling using contextual and environmental information |
US9263042B1 (en) | 2014-07-25 | 2016-02-16 | Google Inc. | Providing pre-computed hotword models |
GB2535766B (en) * | 2015-02-27 | 2019-06-12 | Imagination Tech Ltd | Low power detection of an activation phrase |
US10438593B2 (en) * | 2015-07-22 | 2019-10-08 | Google Llc | Individualized hotword detection models |
JP6463710B2 (en) | 2015-10-16 | 2019-02-06 | グーグル エルエルシー | Hot word recognition |
US9747926B2 (en) | 2015-10-16 | 2017-08-29 | Google Inc. | Hotword recognition |
US9691378B1 (en) * | 2015-11-05 | 2017-06-27 | Amazon Technologies, Inc. | Methods and devices for selectively ignoring captured audio data |
US10095470B2 (en) | 2016-02-22 | 2018-10-09 | Sonos, Inc. | Audio response playback |
US9779735B2 (en) * | 2016-02-24 | 2017-10-03 | Google Inc. | Methods and systems for detecting and processing speech signals |
US10115400B2 (en) | 2016-08-05 | 2018-10-30 | Sonos, Inc. | Multiple voice services |
US10217453B2 (en) * | 2016-10-14 | 2019-02-26 | Soundhound, Inc. | Virtual assistant configured by selection of wake-up phrase |
JP7191819B2 (en) | 2016-10-17 | 2022-12-19 | ハーマン インターナショナル インダストリーズ インコーポレイテッド | Portable audio device with voice capabilities |
US10783883B2 (en) * | 2016-11-03 | 2020-09-22 | Google Llc | Focus session at a voice interface device |
CN111971742A (en) * | 2016-11-10 | 2020-11-20 | 赛轮思软件技术(北京)有限公司 | Techniques for language independent wake word detection |
US10373630B2 (en) | 2017-03-31 | 2019-08-06 | Intel Corporation | Systems and methods for energy efficient and low power distributed automatic speech recognition on wearable devices |
US10916252B2 (en) | 2017-11-10 | 2021-02-09 | Nvidia Corporation | Accelerated data transfer for latency reduction and real-time processing |
US20190237069A1 (en) * | 2018-01-31 | 2019-08-01 | GM Global Technology Operations LLC | Multilingual voice assistance support |
CN108231079B (en) * | 2018-02-01 | 2021-12-07 | 北京百度网讯科技有限公司 | Method, apparatus, device and computer-readable storage medium for controlling electronic device |
CN108509225B (en) * | 2018-03-28 | 2021-07-16 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN108538298B (en) * | 2018-04-04 | 2021-05-04 | 科大讯飞股份有限公司 | Voice wake-up method and device |
US10586538B2 (en) | 2018-04-25 | 2020-03-10 | Comcast Cable Comminications, LLC | Microphone array beamforming control |
US11132989B2 (en) * | 2018-12-13 | 2021-09-28 | Sonos, Inc. | Networked microphone devices, systems, and methods of localized arbitration |
US11587568B2 (en) * | 2020-12-08 | 2023-02-21 | Google Llc | Streaming action fulfillment based on partial hypotheses |
US11948565B2 (en) * | 2020-12-11 | 2024-04-02 | Google Llc | Combining device or assistant-specific hotwords in a single utterance |
DE102021005206B3 (en) * | 2021-10-19 | 2022-11-03 | Mercedes-Benz Group AG | Method and device for determining a multi-part keyword |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5127055A (en) * | 1988-12-30 | 1992-06-30 | Kurzweil Applied Intelligence, Inc. | Speech recognition apparatus & method having dynamic reference pattern adaptation |
US5577164A (en) * | 1994-01-28 | 1996-11-19 | Canon Kabushiki Kaisha | Incorrect voice command recognition prevention and recovery processing method and apparatus |
US5740318A (en) * | 1994-10-18 | 1998-04-14 | Kokusai Denshin Denwa Co., Ltd. | Speech endpoint detection method and apparatus and continuous speech recognition method and apparatus |
US5799273A (en) * | 1996-09-24 | 1998-08-25 | Allvoice Computing Plc | Automated proofreading using interface linking recognized words to their audio data while text is being changed |
US5864805A (en) * | 1996-12-20 | 1999-01-26 | International Business Machines Corporation | Method and apparatus for error correction in a continuous dictation system |
US5905971A (en) * | 1996-05-03 | 1999-05-18 | British Telecommunications Public Limited Company | Automatic speech recognition |
US20030033146A1 (en) * | 2001-08-03 | 2003-02-13 | Morin Philippe R. | Method for efficient, safe and reliable data entry by voice under adverse conditions |
US6535849B1 (en) * | 2000-01-18 | 2003-03-18 | Scansoft, Inc. | Method and system for generating semi-literal transcripts for speech recognition systems |
US20070288241A1 (en) * | 2006-06-13 | 2007-12-13 | Cross Charles W | Oral modification of an asr lexicon of an asr engine |
US20080049908A1 (en) * | 2006-02-10 | 2008-02-28 | Spinvox Limited | Mass-Scale, User-Independent, Device-Independent Voice Messaging System |
US20080120102A1 (en) * | 2006-11-17 | 2008-05-22 | Rao Ashwin P | Predictive speech-to-text input |
US20130173270A1 (en) * | 2011-12-30 | 2013-07-04 | Samsung Electronics Co., Ltd. | Electronic apparatus and method of controlling electronic apparatus |
US20140297287A1 (en) * | 2013-04-01 | 2014-10-02 | David Edward Newman | Voice-Activated Precision Timing |
Family Cites Families (59)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE4130631A1 (en) * | 1991-09-14 | 1993-03-18 | Philips Patentverwaltung | METHOD FOR RECOGNIZING THE SPOKEN WORDS IN A VOICE SIGNAL |
CA2088080C (en) * | 1992-04-02 | 1997-10-07 | Enrico Luigi Bocchieri | Automatic speech recognizer |
GB9223066D0 (en) * | 1992-11-04 | 1992-12-16 | Secr Defence | Children's speech training aid |
US5562453A (en) * | 1993-02-02 | 1996-10-08 | Wen; Sheree H.-R. | Adaptive biofeedback speech tutor toy |
US5621859A (en) * | 1994-01-19 | 1997-04-15 | Bbn Corporation | Single tree method for grammar directed, very large vocabulary speech recognizer |
US5729659A (en) | 1995-06-06 | 1998-03-17 | Potter; Jerry L. | Method and apparatus for controlling a digital computer using oral input |
JP3674990B2 (en) * | 1995-08-21 | 2005-07-27 | セイコーエプソン株式会社 | Speech recognition dialogue apparatus and speech recognition dialogue processing method |
DE69806780T2 (en) * | 1997-09-25 | 2003-03-13 | Tegic Communications Inc | SYSTEM FOR SUPPRESSING AMBIANCE IN A REDUCED KEYBOARD |
US6295391B1 (en) * | 1998-02-19 | 2001-09-25 | Hewlett-Packard Company | Automatic data routing via voice command annotation |
WO2000058946A1 (en) | 1999-03-26 | 2000-10-05 | Koninklijke Philips Electronics N.V. | Client-server speech recognition |
US20050091057A1 (en) * | 1999-04-12 | 2005-04-28 | General Magic, Inc. | Voice application development methodology |
US6178404B1 (en) * | 1999-07-23 | 2001-01-23 | Intervoice Limited Partnership | System and method to facilitate speech enabled user interfaces by prompting with possible transaction phrases |
JP2003514261A (en) | 1999-11-09 | 2003-04-15 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | Speech recognition method for activating hyperlinks on Internet pages |
US6975629B2 (en) * | 2000-03-22 | 2005-12-13 | Texas Instruments Incorporated | Processing packets based on deadline intervals |
US7047196B2 (en) | 2000-06-08 | 2006-05-16 | Agiletv Corporation | System and method of voice recognition near a wireline node of a network supporting cable television and/or video delivery |
TW521266B (en) * | 2000-07-13 | 2003-02-21 | Verbaltek Inc | Perceptual phonetic feature speech recognition system and method |
JP5093963B2 (en) * | 2000-09-08 | 2012-12-12 | ニュアンス コミュニケーションズ オーストリア ゲーエムベーハー | Speech recognition method with replacement command |
US7444286B2 (en) * | 2001-09-05 | 2008-10-28 | Roth Daniel L | Speech recognition using re-utterance recognition |
US8229753B2 (en) | 2001-10-21 | 2012-07-24 | Microsoft Corporation | Web server controls for web enabled recognition and/or audible prompting |
ATE305197T1 (en) * | 2002-04-16 | 2005-10-15 | Bosch Gmbh Robert | METHOD FOR DATA TRANSMISSION IN A COMMUNICATIONS SYSTEM |
US7047200B2 (en) * | 2002-05-24 | 2006-05-16 | Microsoft, Corporation | Voice recognition status display |
CA2411227C (en) | 2002-07-03 | 2007-01-09 | 2012244 Ontario Inc. | System and method of creating and using compact linguistic data |
US7899500B2 (en) * | 2002-09-24 | 2011-03-01 | At&T Intellectual Property I, L. P. | Apparatus and method for providing hands-free operation of a device |
US7603267B2 (en) * | 2003-05-01 | 2009-10-13 | Microsoft Corporation | Rules-based grammar for slots and statistical model for preterminals in natural language understanding system |
US7720683B1 (en) * | 2003-06-13 | 2010-05-18 | Sensory, Inc. | Method and apparatus of specifying and performing speech recognition operations |
US20050043067A1 (en) | 2003-08-21 | 2005-02-24 | Odell Thomas W. | Voice recognition in a vehicle radio system |
US20050154594A1 (en) * | 2004-01-09 | 2005-07-14 | Beck Stephen C. | Method and apparatus of simulating and stimulating human speech and teaching humans how to talk |
US7580841B2 (en) | 2004-09-17 | 2009-08-25 | At&T Intellectual Property I, L.P. | Methods, systems, and computer-readable media for associating dynamic sound content with a web page in a browser |
EP1693829B1 (en) | 2005-02-21 | 2018-12-05 | Harman Becker Automotive Systems GmbH | Voice-controlled data system |
US7826945B2 (en) * | 2005-07-01 | 2010-11-02 | You Zhang | Automobile speech-recognition interface |
US7941316B2 (en) * | 2005-10-28 | 2011-05-10 | Microsoft Corporation | Combined speech and alternate input modality to a mobile device |
US7620553B2 (en) * | 2005-12-20 | 2009-11-17 | Storz Endoskop Produktions Gmbh | Simultaneous support of isolated and connected phrase command recognition in automatic speech recognition systems |
US8521537B2 (en) * | 2006-04-03 | 2013-08-27 | Promptu Systems Corporation | Detection and use of acoustic signal quality indicators |
US7912592B2 (en) * | 2006-06-09 | 2011-03-22 | Garmin International, Inc. | Automatic speech recognition system and method for aircraft |
US7949536B2 (en) * | 2006-08-31 | 2011-05-24 | Microsoft Corporation | Intelligent speech recognition of incomplete phrases |
EP2089877B1 (en) | 2006-11-16 | 2010-04-07 | International Business Machines Corporation | Voice activity detection system and method |
US8949266B2 (en) * | 2007-03-07 | 2015-02-03 | Vlingo Corporation | Multiple web-based content category searching in mobile search application |
US8099289B2 (en) * | 2008-02-13 | 2012-01-17 | Sensory, Inc. | Voice interface and search for electronic devices including bluetooth headsets and remote systems |
GB2468278A (en) * | 2009-03-02 | 2010-09-08 | Sdl Plc | Computer assisted natural language translation outputs selectable target text associated in bilingual corpus with input target text from partial translation |
US8892439B2 (en) | 2009-07-15 | 2014-11-18 | Microsoft Corporation | Combination and federation of local and remote speech recognition |
CN101609671B (en) * | 2009-07-21 | 2011-09-07 | 北京邮电大学 | Method and device for continuous speech recognition result evaluation |
US9111538B2 (en) * | 2009-09-30 | 2015-08-18 | T-Mobile Usa, Inc. | Genius button secondary commands |
US8279052B2 (en) * | 2009-11-04 | 2012-10-02 | Immersion Corporation | Systems and methods for haptic confirmation of commands |
US8515763B2 (en) | 2009-11-24 | 2013-08-20 | Honeywell International Inc. | Methods and systems for utilizing voice commands onboard an aircraft |
US9421475B2 (en) * | 2009-11-25 | 2016-08-23 | Hallmark Cards Incorporated | Context-based interactive plush toy |
US8494852B2 (en) * | 2010-01-05 | 2013-07-23 | Google Inc. | Word-level correction of speech input |
CN102163198B (en) * | 2010-02-24 | 2014-10-22 | 北京搜狗科技发展有限公司 | A method and a system for providing new or popular terms |
US8296151B2 (en) * | 2010-06-18 | 2012-10-23 | Microsoft Corporation | Compound gesture-speech commands |
US9921803B2 (en) | 2010-08-23 | 2018-03-20 | Nokia Technologies Oy | Audio user interface apparatus and method |
US8606581B1 (en) | 2010-12-14 | 2013-12-10 | Nuance Communications, Inc. | Multi-pass speech recognition |
JP5739718B2 (en) * | 2011-04-19 | 2015-06-24 | 本田技研工業株式会社 | Interactive device |
US8984323B2 (en) * | 2011-09-28 | 2015-03-17 | Microchip Technology Incorporated | Scheduling events in a microprocessor using a plurality of delta time registers arranged as a sequence buffer and indicating a sequence position of the sequence buffer to process an event |
US8666751B2 (en) * | 2011-11-17 | 2014-03-04 | Microsoft Corporation | Audio pattern matching for device activation |
US9117449B2 (en) | 2012-04-26 | 2015-08-25 | Nuance Communications, Inc. | Embedded system for construction of small footprint speech recognition with user-definable constraints |
US9275637B1 (en) * | 2012-11-06 | 2016-03-01 | Amazon Technologies, Inc. | Wake word evaluation |
US9633652B2 (en) * | 2012-11-30 | 2017-04-25 | Stmicroelectronics Asia Pacific Pte Ltd. | Methods, systems, and circuits for speaker dependent voice recognition with a single lexicon |
US10395651B2 (en) * | 2013-02-28 | 2019-08-27 | Sony Corporation | Device and method for activating with voice input |
US9361885B2 (en) | 2013-03-12 | 2016-06-07 | Nuance Communications, Inc. | Methods and apparatus for detecting a voice command |
US9218806B1 (en) * | 2013-05-10 | 2015-12-22 | Amazon Technologies, Inc. | Generation and use of multiple speech processing transforms |
-
2013
- 2013-12-04 US US14/096,359 patent/US8768712B1/en active Active
-
2014
- 2014-03-20 US US14/220,781 patent/US9330663B2/en active Active
- 2014-03-21 CN CN201911377903.0A patent/CN111524510B/en active Active
- 2014-03-21 CN CN201480066328.1A patent/CN105793921B/en active Active
- 2014-03-21 EP EP14723220.1A patent/EP3078021B1/en active Active
- 2014-03-21 WO PCT/US2014/031475 patent/WO2015084425A1/en active Application Filing
- 2014-03-21 EP EP18211411.6A patent/EP3483876A1/en not_active Withdrawn
-
2016
- 2016-01-07 US US14/990,462 patent/US9443512B2/en active Active
- 2016-01-08 US US14/991,092 patent/US9502026B2/en active Active
- 2016-06-23 US US15/191,046 patent/US9508342B2/en active Active
- 2016-10-21 US US15/299,853 patent/US9620114B2/en active Active
-
2017
- 2017-03-23 US US15/466,979 patent/US9805719B2/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5127055A (en) * | 1988-12-30 | 1992-06-30 | Kurzweil Applied Intelligence, Inc. | Speech recognition apparatus & method having dynamic reference pattern adaptation |
US5577164A (en) * | 1994-01-28 | 1996-11-19 | Canon Kabushiki Kaisha | Incorrect voice command recognition prevention and recovery processing method and apparatus |
US5740318A (en) * | 1994-10-18 | 1998-04-14 | Kokusai Denshin Denwa Co., Ltd. | Speech endpoint detection method and apparatus and continuous speech recognition method and apparatus |
US5905971A (en) * | 1996-05-03 | 1999-05-18 | British Telecommunications Public Limited Company | Automatic speech recognition |
US5799273A (en) * | 1996-09-24 | 1998-08-25 | Allvoice Computing Plc | Automated proofreading using interface linking recognized words to their audio data while text is being changed |
US5864805A (en) * | 1996-12-20 | 1999-01-26 | International Business Machines Corporation | Method and apparatus for error correction in a continuous dictation system |
US6535849B1 (en) * | 2000-01-18 | 2003-03-18 | Scansoft, Inc. | Method and system for generating semi-literal transcripts for speech recognition systems |
US20030033146A1 (en) * | 2001-08-03 | 2003-02-13 | Morin Philippe R. | Method for efficient, safe and reliable data entry by voice under adverse conditions |
US20080049908A1 (en) * | 2006-02-10 | 2008-02-28 | Spinvox Limited | Mass-Scale, User-Independent, Device-Independent Voice Messaging System |
US20070288241A1 (en) * | 2006-06-13 | 2007-12-13 | Cross Charles W | Oral modification of an asr lexicon of an asr engine |
US20080120102A1 (en) * | 2006-11-17 | 2008-05-22 | Rao Ashwin P | Predictive speech-to-text input |
US20130173270A1 (en) * | 2011-12-30 | 2013-07-04 | Samsung Electronics Co., Ltd. | Electronic apparatus and method of controlling electronic apparatus |
US20140297287A1 (en) * | 2013-04-01 | 2014-10-02 | David Edward Newman | Voice-Activated Precision Timing |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9775113B2 (en) | 2014-12-11 | 2017-09-26 | Mediatek Inc. | Voice wakeup detecting device with digital microphone and associated method |
US9779725B2 (en) * | 2014-12-11 | 2017-10-03 | Mediatek Inc. | Voice wakeup detecting device and method |
US20160171975A1 (en) * | 2014-12-11 | 2016-06-16 | Mediatek Inc. | Voice wakeup detecting device and method |
DE102016118680B4 (en) | 2015-10-01 | 2021-11-04 | Lenovo (Singapore) Pte. Ltd. | Situation-dependent cancellation of a wake-up word to activate a voice command input |
US9542941B1 (en) * | 2015-10-01 | 2017-01-10 | Lenovo (Singapore) Pte. Ltd. | Situationally suspending wakeup word to enable voice command input |
EP3751561A3 (en) * | 2015-10-16 | 2020-12-30 | Google LLC | Hotword recognition |
US11429883B2 (en) | 2015-11-13 | 2022-08-30 | Microsoft Technology Licensing, Llc | Enhanced computer experience from activity prediction |
US10769189B2 (en) | 2015-11-13 | 2020-09-08 | Microsoft Technology Licensing, Llc | Computer speech recognition and semantic understanding from activity patterns |
US10438583B2 (en) * | 2016-07-20 | 2019-10-08 | Lenovo (Singapore) Pte. Ltd. | Natural language voice assistant |
US10621992B2 (en) | 2016-07-22 | 2020-04-14 | Lenovo (Singapore) Pte. Ltd. | Activating voice assistant based on at least one of user proximity and context |
US20180121161A1 (en) * | 2016-10-28 | 2018-05-03 | Kyocera Corporation | Electronic device, control method, and storage medium |
US10210866B2 (en) | 2017-01-20 | 2019-02-19 | Essential Products, Inc. | Ambient assistant device |
US10102856B2 (en) * | 2017-01-20 | 2018-10-16 | Essential Products, Inc. | Assistant device with active and passive experience modes |
US10706851B2 (en) | 2017-02-14 | 2020-07-07 | Google Llc | Server side hotwording |
EP3767623A1 (en) * | 2017-02-14 | 2021-01-20 | Google LLC | Server side hotwording |
US11049504B2 (en) | 2017-02-14 | 2021-06-29 | Google Llc | Server side hotwording |
US10311876B2 (en) | 2017-02-14 | 2019-06-04 | Google Llc | Server side hotwording |
WO2018151772A1 (en) * | 2017-02-14 | 2018-08-23 | Google Llc | Server side hotwording |
US11699443B2 (en) | 2017-02-14 | 2023-07-11 | Google Llc | Server side hotwording |
US10664533B2 (en) | 2017-05-24 | 2020-05-26 | Lenovo (Singapore) Pte. Ltd. | Systems and methods to determine response cue for digital assistant based on context |
US20210134272A1 (en) * | 2018-07-20 | 2021-05-06 | Sony Corporation | Information processing device, information processing system, information processing method, and program |
US10984783B2 (en) * | 2019-03-27 | 2021-04-20 | Intel Corporation | Spoken keyword detection based utterance-level wake on intent system |
US20230019595A1 (en) * | 2020-02-07 | 2023-01-19 | Sonos, Inc. | Localized Wakeword Verification |
EP4057278A1 (en) * | 2021-03-10 | 2022-09-14 | Comcast Cable Communications, LLC | Systems and methods for improved speech and command detection |
US11961519B2 (en) * | 2022-04-18 | 2024-04-16 | Sonos, Inc. | Localized wakeword verification |
Also Published As
Publication number | Publication date |
---|---|
EP3078021B1 (en) | 2018-12-12 |
US20170040020A1 (en) | 2017-02-09 |
US9805719B2 (en) | 2017-10-31 |
US20160125875A1 (en) | 2016-05-05 |
US20160300568A1 (en) | 2016-10-13 |
CN105793921B (en) | 2020-01-17 |
US9443512B2 (en) | 2016-09-13 |
US9620114B2 (en) | 2017-04-11 |
WO2015084425A1 (en) | 2015-06-11 |
CN111524510B (en) | 2022-03-22 |
US20170193998A1 (en) | 2017-07-06 |
EP3078021A1 (en) | 2016-10-12 |
US8768712B1 (en) | 2014-07-01 |
US9502026B2 (en) | 2016-11-22 |
CN105793921A (en) | 2016-07-20 |
US20160118040A1 (en) | 2016-04-28 |
US9508342B2 (en) | 2016-11-29 |
CN111524510A (en) | 2020-08-11 |
US9330663B2 (en) | 2016-05-03 |
EP3483876A1 (en) | 2019-05-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9508342B2 (en) | Initiating actions based on partial hotwords | |
US11842045B2 (en) | Modality learning on mobile devices | |
US10269346B2 (en) | Multiple speech locale-specific hotword classifiers for selection of a speech locale | |
JP6630765B2 (en) | Individualized hotword detection model | |
US9401146B2 (en) | Identification of communication-related voice commands | |
US20160055847A1 (en) | System and method for speech validation | |
US20150127345A1 (en) | Name Based Initiation of Speech Recognition | |
US20160027435A1 (en) | Method for training an automatic speech recognition system | |
US10133821B2 (en) | Search result prefetching of voice queries |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: GOOGLE INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SHARIFI, MATTHEW;REEL/FRAME:032841/0167 Effective date: 20131203 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
AS | Assignment |
Owner name: GOOGLE LLC, CALIFORNIA Free format text: CHANGE OF NAME;ASSIGNOR:GOOGLE INC.;REEL/FRAME:044566/0657 Effective date: 20170929 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 8 |